Search

Current state-of-the-art methods for human image customized synthesis typically require tedious training on large-scale datasets. In such cases, they are prone to overfitting and struggle to personalize individuals of unseen styles. Moreover, these methods extensively focus on single-concept human image synthesis and lack the flexibility needed for customizing individuals with multiple given concepts, thereby impeding their broader practical application. To this end, we propose MagicFace, a novel training-free method for universal-style human image personalized synthesis, enabling multi-concept customization by accurately integrating reference concept features into their latent generated region at the pixel level. Specifically, MagicFace introduces a coarse-to-fine generation pipeline, involving two sequential stages: semantic layout construction and concept feature injection. This is achieved by our Reference-aware Self-Attention (RSA) and Region-grouped Blend Attention (RBA) mechanisms. In the first stage, RSA enables the latent image to query features from all reference concepts simultaneously, extracting the overall semantic understanding to facilitate the initial semantic layout establishment. In the second stage, we employ an attention-based semantic segmentation method to pinpoint the latent generated regions of all concepts at each step. Following this, RBA divides the pixels of the latent image into semantic groups, with each group querying fine-grained features from the corresponding reference concept, which ensures precise attribute alignment and feature injection. Throughout the generation process, a weighted mask strategy is employed to ensure the model focuses more on the reference concepts. Extensive experiments demonstrate the superiority of MagicFace in both human-centric subject-to-image synthesis and multi-concept human image customization., Comment: project page: https://codegoat24.github.io/MagicFace

Deep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representation from single color model with a specific mapping function, a.k.a., color space, during the colorization pipeline. In this paper, we first investigate the modeling of different color spaces, and find each of them exhibiting distinctive characteristics with unique distribution of colors. The complementarity among multiple color spaces leads to benefits for the image colorization task. We present MultiColor, a new learning-based approach to automatically colorize grayscale images that combines clues from multiple color spaces. Specifically, we employ a set of dedicated colorization modules for individual color space. Within each module, a transformer decoder is first employed to refine color query embeddings and then a color mapper produces color channel prediction using the embeddings and semantic features. With these predicted color channels representing various color spaces, a complementary network is designed to exploit the complementarity and generate pleasing and reasonable colorized images. We conduct extensive experiments on real-world datasets, and the results demonstrate superior performance over the state-of-the-arts.

Escape of active agents from metastable states is of great interest in statistical and biological physics. In this study, we investigate the escape of a flexible active ring, composed of active Brownian particles, from a flat attractive surface using Brownian dynamics simulations. To systematically explore the effects of activity, persistence time, and the shape of attractive potentials, we calculate escape time and effective temperature. We observe two distinct escape mechanisms: Kramers-like thermal activation at small persistence times and the maximal force problem at large persistence time, where escape time is determined by persistence time. The escape time explicitly depends on the shape of the potential barrier at high activity and large persistence time. Moreover, when the propulsion force is biased along the ring's contour, escape becomes more difficult and is primarily driven by thermal noise. Our findings highlight that, despite its intricate configuration, the active ring can be effectively modeled as a self-propelled Brownian particle when studying its escape from a smooth surface.

It has been supposed that the interplay of elasticity and activity plays a key role in triggering the non-equilibrium behaviors in biological systems. However, the experimental model system is missing to investigate the spatiotemporally dynamical phenomena. Here, a model system of an active chain, where active eccentric-disks are linked by a spring, is designed to study the interplay of activity, elasticity, and friction. Individual active chain exhibits longitudinal and transverse motion, however, it starts to self-rotate when pinning one end, and self-beats when clamping one end. Additionally, our eccentric-disk model can qualitatively reproduce such behaviors and explain the unusual self-rotation of the first disk around its geometric center. Further, the structure and dynamics of long chains were studied via simulations without steric interactions. It was found that hairpin conformation emerges in free motion, while in the constrained motions, the rotational and beating frequencies scale with the flexure number (the ratio of self-propelling force to bending rigidity), ~4/3. Scaling analysis suggests that it results from the balance between activity and energy dissipation. Our findings show that topological constraints play a vital role in non-equilibrium synergy behavior.

Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath). The generalization ability of foundation models is crucial for the success in various downstream clinical tasks. However, current foundation models have only been evaluated on a limited type and number of tasks, leaving their generalization ability and overall performance unclear. To address this gap, we established a most comprehensive benchmark to evaluate the performance of off-the-shelf foundation models across six distinct clinical task types, encompassing a total of 39 specific tasks. Our findings reveal that existing foundation models excel at certain task types but struggle to effectively handle the full breadth of clinical tasks. To improve the generalization of pathology foundation models, we propose a unified knowledge distillation framework consisting of both expert and self knowledge distillation, where the former allows the model to learn from the knowledge of multiple expert models, while the latter leverages self-distillation to enable image representation learning via local-global alignment. Based on this framework, a Generalizable Pathology Foundation Model (GPFM) is pretrained on a large-scale dataset consisting of 190 million images from around 86,000 public H&E whole slides across 34 major tissue types. Evaluated on the established benchmark, GPFM achieves an impressive average rank of 1.36, with 29 tasks ranked 1st, while the the second-best model, UNI, attains an average rank of 2.96, with only 4 tasks ranked 1st. The superior generalization of GPFM demonstrates its exceptional modeling capabilities across a wide range of clinical tasks, positioning it as a new cornerstone for feature representation in CPath.

In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casting formulation to aggregate multiple estimates from different viewing positions, enabling the computation of reliable pseudo-labels for self-training. In particular, our ray-casting approach enforces multi-view consistency along all ray directions and prioritizes spatial proximity to the camera view for geometry reasoning. As a result, our geometry-aware pseudo-labels effectively handle complex room geometries and occluded walls without relying on assumptions such as Manhattan World or planar room walls. Evaluation on publicly available datasets, including synthetic and real-world scenarios, demonstrates significant improvements in current state-of-the-art layout models without using any human annotation., Comment: Accepted to ECCV-2024

For image inpainting, the existing Denoising Diffusion Probabilistic Model (DDPM) based method i.e. RePaint can produce high-quality images for any inpainting form. It utilizes a pre-trained DDPM as a prior and generates inpainting results by conditioning on the reverse diffusion process, namely denoising process. However, this process is significantly time-consuming. In this paper, we propose an efficient DDPM-based image inpainting method which includes three speed-up strategies. First, we utilize a pre-trained Light-Weight Diffusion Model (LWDM) to reduce the number of parameters. Second, we introduce a skip-step sampling scheme of Denoising Diffusion Implicit Models (DDIM) for the denoising process. Finally, we propose Coarse-to-Fine Sampling (CFS), which speeds up inference by reducing image resolution in the coarse stage and decreasing denoising timesteps in the refinement stage. We conduct extensive experiments on both faces and general-purpose image inpainting tasks, and our method achieves competitive performance with approximately 60 times speedup., Comment: The code is avaliable at: https://github.com/linghuyuhangyuan/M2S

When dealing with the task of fine-grained scene image classification, most previous works lay much emphasis on global visual features when doing multi-modal feature fusion. In other words, models are deliberately designed based on prior intuitions about the importance of different modalities. In this paper, we present a new multi-modal feature fusion approach named MAA (Modality-Agnostic Adapter), trying to make the model learn the importance of different modalities in different cases adaptively, without giving a prior setting in the model architecture. More specifically, we eliminate the modal differences in distribution and then use a modality-agnostic Transformer encoder for a semantic-level feature fusion. Our experiments demonstrate that MAA achieves state-of-the-art results on benchmarks by applying the same modalities with previous methods. Besides, it is worth mentioning that new modalities can be easily added when using MAA and further boost the performance. Code is available at https://github.com/quniLcs/MAA.

The efficient compression of large language models (LLMs) is becoming increasingly popular. However, recovering the accuracy of compressed LLMs is still a major challenge. Structural pruning with standard Low-Rank Adaptation (LoRA) is a common technique in current LLM compression. In structural pruning, the model architecture is modified unevenly, resulting in suboptimal performance in various downstream tasks via standard LoRA with fixed rank. To address this problem, we introduce RankAdaptor, an efficient fine-tuning method with hierarchical dynamic rank scheduling for pruned LLMs. An end-to-end automatic optimization flow is developed that utilizes a lightweight performance model to determine the different ranks during fine-tuning. Comprehensive experiments on popular benchmarks show that RankAdaptor consistently outperforms standard LoRA with structural pruning over different pruning settings. Without increasing the trainable parameters, RankAdaptor further reduces the accuracy performance gap between the recovery of the pruned model and the original model compared to standard LoRA.

We adopt the effective Lagrangian approach to study the strong decays of the $1^-(0^{++})$ $D^\ast\bar{D}^\ast$ molecular state [denoted as $T_{\psi0}^a(4010)$ according to the LHCb naming convention] through triangle diagrams. The decay channels include the open-charm $D\bar{D}$, and the hidden-charm $\eta_c\pi$, $J/\psi\rho$, and $\chi_{c1}\pi$. The coupling between the $T_{\psi0}^a(4010)$ and its constituents $D^\ast\bar{D}^\ast$ is obtained by solving for the residue of the scattering T-matrix at the pole. Our calculation yields a total width of $(12.0$$-$$35.4)$ MeV for the $T_{\psi0}^a(4010)$ state, with its main decay channels being $\eta_c\pi$ and $\chi_{c1}\pi$. The $X(4100)$ and $X(4050)$ have similar masses and widths, with both masses being close to the $D^\ast\bar{D}^\ast$ threshold. Additionally, their decay final states are consistent with those of the $T_{\psi0}^a(4010)$. Therefore, it is likely that they represent the same state and both potentially correspond to the $T_{\psi0}^a(4010)$. We suggest that future experiments focus on searching for the $T_{\psi0}^a(4010)$ signal in the final states $\eta_c\pi^-$, $\chi_{c1}\pi^-$ and $D^0D^-$ of the $B^0\to\eta_c\pi^-K^+$, $\chi_{c1}\pi^- K^+$ and $D^0D^-K^+$ processes, respectively, as well as further investigating its resonance parameters with Flatt\'e-like formula., Comment: 9 pages, 6 figures

The recent emergence of diffusion models has significantly advanced the precision of learnable priors, presenting innovative avenues for addressing inverse problems. Since inverse problems inherently entail maximum a posteriori estimation, previous works have endeavored to integrate diffusion priors into the optimization frameworks. However, prevailing optimization-based inverse algorithms primarily exploit the prior information within the diffusion models while neglecting their denoising capability. To bridge this gap, this work leverages the diffusion process to reframe noisy inverse problems as a two-variable constrained optimization task by introducing an auxiliary optimization variable. By employing gradient truncation, the projection gradient descent method is efficiently utilized to solve the corresponding optimization problem. The proposed algorithm, termed ProjDiff, effectively harnesses the prior information and the denoising capability of a pre-trained diffusion model within the optimization framework. Extensive experiments on the image restoration tasks and source separation and partial generation tasks demonstrate that ProjDiff exhibits superior performance across various linear and nonlinear inverse problems, highlighting its potential for practical applications. Code is available at https://github.com/weigerzan/ProjDiff/.

Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-level guidance during training. Besides, their text encoders, pre-trained on a single font type, struggle to adapt to the diverse font styles encountered in practical applications. Consequently, these methods suffer from character distortion, repetition, and absence, particularly in polystylistic scenarios. To this end, this paper proposes DreamText for high-fidelity scene text synthesis. Our key idea is to reconstruct the diffusion training process, introducing more refined guidance tailored to this task, to expose and rectify the model's attention at the character level and strengthen its learning of text regions. This transformation poses a hybrid optimization challenge, involving both discrete and continuous variables. To effectively tackle this challenge, we employ a heuristic alternate optimization strategy. Meanwhile, we jointly train the text encoder and generator to comprehensively learn and utilize the diverse font present in the training dataset. This joint training is seamlessly integrated into the alternate optimization process, fostering a synergistic relationship between learning character embedding and re-estimating character attention. Specifically, in each step, we first encode potential character-generated position information from cross-attention maps into latent character masks. These masks are then utilized to update the representation of specific characters in the current step, which, in turn, enables the generator to correct the character's attention in the subsequent steps. Both qualitative and quantitative results demonstrate the superiority of our method to the state of the art., Comment: Code: https://github.com/CodeGoat24/DreamText, Project page: https://codegoat24.github.io/DreamText/

Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation. Despite its potential, the \textit{weak teacher challenge} arises due to repetitive and non-diverse car camera images and sparse, inaccurate ground truth labels. To address this, we propose the Efficient Image-to-LiDAR Knowledge Transfer (ELiTe) paradigm. ELiTe introduces Patch-to-Point Multi-Stage Knowledge Distillation, transferring comprehensive knowledge from the Vision Foundation Model (VFM), extensively trained on diverse open-world images. This enables effective knowledge transfer to a lightweight student model across modalities. ELiTe employs Parameter-Efficient Fine-Tuning to strengthen the VFM teacher and expedite large-scale model training with minimal costs. Additionally, we introduce the Segment Anything Model based Pseudo-Label Generation approach to enhance low-quality image labels, facilitating robust semantic representations. Efficient knowledge transfer in ELiTe yields state-of-the-art results on the SemanticKITTI benchmark, outperforming real-time inference models. Our approach achieves this with significantly fewer parameters, confirming its effectiveness and efficiency., Comment: 9 pages, 6 figures, ICME 2024 oral

This paper presents a robust fine-tuning method designed for pre-trained 3D point cloud models, to enhance feature robustness in downstream fine-tuned models. We highlight the limitations of current fine-tuning methods and the challenges of learning robust models. The proposed method, named Weight-Space Ensembles for Fine-Tuning then Linear Probing (WiSE-FT-LP), integrates the original pre-training and fine-tuning models through weight space integration followed by Linear Probing. This approach significantly enhances the performance of downstream fine-tuned models under distribution shifts, improving feature robustness while maintaining high performance on the target distribution. We apply this robust fine-tuning method to mainstream 3D point cloud pre-trained models and evaluate the quality of model parameters and the degradation of downstream task performance. Experimental results demonstrate the effectiveness of WiSE-FT-LP in enhancing model robustness, effectively balancing downstream task performance and model feature robustness without altering the model structures., Comment: 9 pages, 5 figures

Inherent ambiguity in layout annotations poses significant challenges to developing accurate 360{\deg} room layout estimation models. To address this issue, we propose a novel Bi-Layout model capable of predicting two distinct layout types. One stops at ambiguous regions, while the other extends to encompass all visible areas. Our model employs two global context embeddings, where each embedding is designed to capture specific contextual information for each layout type. With our novel feature guidance module, the image feature retrieves relevant context from these embeddings, generating layout-aware features for precise bi-layout predictions. A unique property of our Bi-Layout model is its ability to inherently detect ambiguous regions by comparing the two predictions. To circumvent the need for manual correction of ambiguous annotations during testing, we also introduce a new metric for disambiguating ground truth layouts. Our method demonstrates superior performance on benchmark datasets, notably outperforming leading approaches. Specifically, on the MatterportLayout dataset, it improves 3DIoU from 81.70% to 82.57% across the full test set and notably from 54.80% to 59.97% in subsets with significant ambiguity. Project page: https://liagm.github.io/Bi_Layout/, Comment: CVPR 2024, Project page: https://liagm.github.io/Bi_Layout/

We prove the Hardy-Littlewood-Sobolev type $L^p$ estimates for the gain term of the Boltzmann collision operator including Maxwellian molecule, hard potential and hard sphere models. Combining with the results of Alonso et al. [2] for the soft potential and Maxwellian molecule models, we provide an unified form of $L^p$ estimates for all cutoff models which are sharp in the sense of scaling. The most striking feature of our new estimates for the hard potential and hard sphere models is that they do not increase the moment, the same as Maxwellian molecule and soft potential models. Based on these novelties, we prove the global existence and scattering of the non-negative unique mild solution for the Cauchy problem of the Boltzmann equation when the positive initial data is small in the weighted $L^3_{x,v}$ space.

Scene text image super-resolution has significantly improved the accuracy of scene text recognition. However, many existing methods emphasize performance over efficiency and ignore the practical need for lightweight solutions in deployment scenarios. Faced with the issues, our work proposes an efficient framework called SGENet to facilitate deployment on resource-limited platforms. SGENet contains two branches: super-resolution branch and semantic guidance branch. We apply a lightweight pre-trained recognizer as a semantic extractor to enhance the understanding of text information. Meanwhile, we design the visual-semantic alignment module to achieve bidirectional alignment between image features and semantics, resulting in the generation of highquality prior guidance. We conduct extensive experiments on benchmark dataset, and the proposed SGENet achieves excellent performance with fewer computational costs. Code is available at https://github.com/SijieLiu518/SGENet

Image composition involves seamlessly integrating given objects into a specific visual context. Current training-free methods rely on composing attention weights from several samplers to guide the generator. However, since these weights are derived from disparate contexts, their combination leads to coherence confusion and loss of appearance information. These issues worsen with their excessive focus on background generation, even when unnecessary in this task. This not only impedes their swift implementation but also compromises foreground generation quality. Moreover, these methods introduce unwanted artifacts in the transition area. In this paper, we formulate image composition as a subject-based local editing task, solely focusing on foreground generation. At each step, the edited foreground is combined with the noisy background to maintain scene consistency. To address the remaining issues, we propose PrimeComposer, a faster training-free diffuser that composites the images by well-designed attention steering across different noise levels. This steering is predominantly achieved by our Correlation Diffuser, utilizing its self-attention layers at each step. Within these layers, the synthesized subject interacts with both the referenced object and background, capturing intricate details and coherent relationships. This prior information is encoded into the attention weights, which are then integrated into the self-attention layers of the generator to guide the synthesis process. Besides, we introduce a Region-constrained Cross-Attention to confine the impact of specific subject-related tokens to desired regions, addressing the unwanted artifacts shown in the prior method thereby further improving the coherence in the transition area. Our method exhibits the fastest inference efficiency and extensive experiments demonstrate our superiority both qualitatively and quantitatively., Comment: Accepted by ACMMM2024. Code: https://github.com/CodeGoat24/PrimeComposer

Out-of-distribution detection (OOD) is a crucial technique for deploying machine learning models in the real world to handle the unseen scenarios. In this paper, we first propose a simple yet effective Neural Activation Prior (NAP) for OOD detection. Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few neurons being activated with a large response by an in-distribution (ID) sample is significantly higher than that by an OOD sample. An intuitive explanation is that for a model fully trained on ID dataset, each channel would play a role in detecting a certain pattern in the ID dataset, and a few neurons can be activated with a large response when the pattern is detected in an input sample. Then, a new scoring function based on this prior is proposed to highlight the role of these strongly activated neurons in OOD detection. Our approach is plug-and-play and does not lead to any performance degradation on ID data classification and requires no extra training or statistics from training or external datasets. Notice that previous methods primarily rely on post-global-pooling features of the neural networks, while the within-channel distribution information we leverage would be discarded by the global pooling operator. Consequently, our method is orthogonal to existing approaches and can be effectively combined with them in various applications. Experimental results show that our method achieves the state-of-the-art performance on CIFAR benchmark and ImageNet dataset, which demonstrates the power of the proposed prior. Finally, we extend our method to Transformers and the experimental findings indicate that NAP can also significantly enhance the performance of OOD detection on Transformers, thereby demonstrating the broad applicability of this prior knowledge.

The decay of sunspot plays a key role in magnetic flux transportation in solar active regions (ARs). To better understand the physical mechanism of the entire decay process of a sunspot, an {\alpha}-configuration sunspot in AR NOAA 12411 was studied. Based on the continuum intensity images and vector magnetic field data with stray light correction from Solar Dynamics Observatory/Helioseismic and Magnetic Imager, the area, vector magnetic field and magnetic flux in the umbra and penumbra are calculated with time, respectively. Our main results are as follows: (1) The decay curves of the sunspot area in its umbra, penumbra, and whole sunspot take the appearance of Gaussian profiles. The area decay rates of the umbra, penumbra and whole sunspot are -1.56 MSH/day, -12.61 MSH/day and -14.04 MSH/day, respectively; (2) With the decay of the sunspot, the total magnetic field strength and the vertical component of the penumbra increase, and the magnetic field of the penumbra becomes more vertical. Meanwhile, the total magnetic field strength and vertical magnetic field strength for the umbra decrease, and the inclination angle changes slightly with an average value of about 20{\deg}; (3) The magnetic flux decay curves of the sunspot in its umbra, penumbra, and whole sunspot exhibit quadratic patterns, their magnetic flux decay rates of the umbra, penumbra and whole sunspot are -9.84 * 10^19 Mx/day, -1.59 * 10^20 Mx/day and -2.60 * 10^20 Mx/day , respectively. The observation suggests that the penumbra may be transformed into the umbra, resulting in the increase of the average vertical magnetic field strength and the reduction of the inclination angle in the penumbra during the decay of the sunspot.

Out-of-distribution (OOD) detection plays a crucial role in ensuring the security of neural networks. Existing works have leveraged the fact that In-distribution (ID) samples form a subspace in the feature space, achieving state-of-the-art (SOTA) performance. However, the comprehensive characteristics of the ID subspace still leave under-explored. Recently, the discovery of Neural Collapse ($\mathcal{NC}$) sheds light on novel properties of the ID subspace. Leveraging insight from $\mathcal{NC}$, we observe that the Principal Angle between the features and the ID feature subspace forms a superior representation for measuring the likelihood of OOD. Building upon this observation, we propose a novel $\mathcal{NC}$-inspired OOD scoring function, named Entropy-enhanced Principal Angle (EPA), which integrates both the global characteristic of the ID subspace and its inner property. We experimentally compare EPA with various SOTA approaches, validating its superior performance and robustness across different network architectures and OOD datasets., Comment: Accepted by ICASSP 2024

Reducing the in-band and co-polarization radar cross section (RCS) of antennas is a widely concerned problem, especially for bistatic RCS reduction of a single antenna. Therefore, this letter presents a design method to control the null of the in-band scattering field by controlling the load impedance of the antenna, so as to effectively reduce the bistatic RCS. First, the relationship between the null position and the load impedance is calculated by analyzing the in-band scattering field of the antenna. Then, the load impedance of the traditional patch antenna is controlled by cascading an open-circuit stub of different lengths on the feeding line, so as to realize the null tunning of the in-band scattering field. Simulated and measured results show that the designed patch antenna can tune the scattering pattern null from 0{\deg} to 60{\deg} thus effectively reduce the bistatic RCS under the premise that the radiation performance is basically unchanged.

Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the others, resulting in poor diversity and fidelity. In addition, some methods lack constraints between parts, which need manual selections of edited results to ensure quality. Therefore, we propose a four-stage process for point cloud part editing: Segmentation, Generation, Assembly, and Selection. Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint. By independently fitting part-level feature distributions, we realize the feature disentanglement. By explicitly modeling the transformation from object-level distribution to part-level distributions, we realize the feature constraint. Considerable experiments on different datasets demonstrate the efficiency and effectiveness of SGAS on point cloud part editing. In addition, SGAS can be pruned to realize unsupervised part-aware point cloud generation and achieves state-of-the-art results., Comment: 9 pages, 7 figures, AAAI 2024

In computational pathology, whole-slide image (WSI) classification presents a formidable challenge due to its gigapixel resolution and limited fine-grained annotations. Multiple-instance learning (MIL) offers a weakly supervised solution, yet refining instance-level information from bag-level labels remains challenging. While most of the conventional MIL methods use attention scores to estimate instance importance scores (IIS) which contribute to the prediction of the slide labels, these often lead to skewed attention distributions and inaccuracies in identifying crucial instances. To address these issues, we propose a new approach inspired by cooperative game theory: employing Shapley values to assess each instance's contribution, thereby improving IIS estimation. The computation of the Shapley value is then accelerated using attention, meanwhile retaining the enhanced instance identification and prioritization. We further introduce a framework for the progressive assignment of pseudo bags based on estimated IIS, encouraging more balanced attention distributions in MIL models. Our extensive experiments on CAMELYON-16, BRACS, TCGA-LUNG, and TCGA-BRCA datasets show our method's superiority over existing state-of-the-art approaches, offering enhanced interpretability and class-wise insights. Our source code is available at https://github.com/RenaoYan/PMIL., Comment: IEEE TRANSACTIONS ON MEDICAL IMAGING 2024

With the increasing prevalence of smartphones and websites, Image Aesthetic Assessment (IAA) has become increasingly crucial. While the significance of attributes in IAA is widely recognized, many attribute-based methods lack consideration for the selection and utilization of aesthetic attributes. Our initial step involves the acquisition of aesthetic attributes from both intra- and inter-perspectives. Within the intra-perspective, we extract the direct visual attributes of images, constituting the absolute attribute. In the inter-perspective, our focus lies in modeling the relative score relationships between images within the same sequence, forming the relative attribute. Then, to better utilize image attributes in aesthetic assessment, we propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images. For absolute attributes, we leverage multiple absolute-attribute perception modules and an absolute-attribute interacting network. The absolute-attribute perception modules are first pre-trained on several absolute-attribute learning tasks and then used to extract corresponding absolute attribute features. The absolute-attribute interacting network adaptively learns the weight of diverse absolute-attribute features, effectively integrating them with generic aesthetic features from various absolute-attribute perspectives and generating the aesthetic prediction. To model the relative attribute of images, we consider the relative ranking and relative distance relationships between images in a Relative-Relation Loss function, which boosts the robustness of the UMAAF. Furthermore, UMAAF achieves state-of-the-art performance on TAD66K and AVA datasets, and multiple experiments demonstrate the effectiveness of each module and the model's alignment with human preference.

Layout-to-image synthesis is an emerging technique in conditional image generation. It aims to generate complex scenes, where users require fine control over the layout of the objects in a scene. However, it remains challenging to control the object coherence, including semantic coherence (e.g., the cat looks at the flowers or not) and physical coherence (e.g., the hand and the racket should not be misaligned). In this paper, we propose a novel diffusion model with effective global semantic fusion (GSF) and self-similarity feature enhancement modules to guide the object coherence for this task. For semantic coherence, we argue that the image caption contains rich information for defining the semantic relationship within the objects in the images. Instead of simply employing cross-attention between captions and latent images, which addresses the highly relevant layout restriction and semantic coherence requirement separately and thus leads to unsatisfying results shown in our experiments, we develop GSF to fuse the supervision from the layout restriction and semantic coherence requirement and exploit it to guide the image synthesis process. Moreover, to improve the physical coherence, we develop a Self-similarity Coherence Attention (SCA) module to explicitly integrate local contextual physical coherence relation into each pixel's generation process. Specifically, we adopt a self-similarity map to encode the physical coherence restrictions and employ it to extract coherent features from text embedding. Through visualization of our self-similarity map, we explore the essence of SCA, revealing that its effectiveness is not only in capturing reliable physical coherence patterns but also in enhancing complex texture generation. Extensive experiments demonstrate the superiority of our proposed method in both image generation quality and controllability., Comment: Code: https://github.com/CodeGoat24/EOCNet

Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which involves an irreconcilable training imbalance. Precisely, to generate realistic persons, they need to sufficiently tune the pre-trained model, which inevitably causes the model to forget the rich semantic scene prior and makes scene generation over-fit to the training data. Moreover, even with sufficient fine-tuning, these methods can still not generate high-fidelity persons since joint learning of the scene and person generation also lead to quality compromise. In this paper, we propose Face-diffuser, an effective collaborative generation pipeline to eliminate the above training imbalance and quality compromise. Specifically, we first develop two specialized pre-trained diffusion models, i.e., Text-driven Diffusion Model (TDM) and Subject-augmented Diffusion Model (SDM), for scene and person generation, respectively. The sampling process is divided into three sequential stages, i.e., semantic scene construction, subject-scene fusion, and subject enhancement. The first and last stages are performed by TDM and SDM respectively. The subject-scene fusion stage, that is the collaboration achieved through a novel and highly effective mechanism, Saliency-adaptive Noise Fusion (SNF). Specifically, it is based on our key observation that there exists a robust link between classifier-free guidance responses and the saliency of generated images. In each time step, SNF leverages the unique strengths of each model and allows for the spatial blending of predicted noises from both models automatically in a saliency-aware manner. Extensive experiments confirm the impressive effectiveness and robustness of the Face-diffuser., Comment: Accepted by CVPR2024. Code: https://github.com/CodeGoat24/Face-diffuser

Visually-situated languages such as charts and plots are omnipresent in real-world documents. These graphical depictions are human-readable and are often analyzed in visually-rich documents to address a variety of questions that necessitate complex reasoning and common-sense responses. Despite the growing number of datasets that aim to answer questions over charts, most only address this task in isolation, without considering the broader context of document-level question answering. Moreover, such datasets lack adequate common-sense reasoning information in their questions. In this work, we introduce a novel task named document-level chart question answering (DCQA). The goal of this task is to conduct document-level question answering, extracting charts or plots in the document via document layout analysis (DLA) first and subsequently performing chart question answering (CQA). The newly developed benchmark dataset comprises 50,010 synthetic documents integrating charts in a wide range of styles (6 styles in contrast to 3 for PlotQA and ChartQA) and includes 699,051 questions that demand a high degree of reasoning ability and common-sense understanding. Besides, we present the development of a potent question-answer generation engine that employs table data, a rich color set, and basic question templates to produce a vast array of reasoning question-answer pairs automatically. Based on DCQA, we devise an OCR-free transformer for document-level chart-oriented understanding, capable of DLA and answering complex reasoning and common-sense questions over charts in an OCR-free manner. Our DCQA dataset is expected to foster research on understanding visualizations in documents, especially for scenarios that require complex reasoning for charts in the visually-rich document. We implement and evaluate a set of baselines, and our proposed method achieves comparable results.

The PZT/FeGa thin film memtranstor was prepared and the modulation of the magnetoelectric coefficient by external magnetic and electric fields was studied. The magnetoelectric coefficient of the PZT/FeGa memtranstor can be reversed by flipping the direction of magnetization of FeGa or ferroelectric polarization of PZT. Notably, the sign of the magnetoelectric coefficient can be switched repeatedly by reversing ferroelectric polarization of PZT when the external magnetic field remains constant. Moreover, the binary switching behavior can still be maintained under zero DC bias magnetic field. When the polarization direction remains stable, the magnetoelectric coefficient also does not change. This means that the magnetoelectric coefficient of PZT/FeGa is non-volatile. Furthermore, the retention and endurance characteristics of the PZT/FeGa thin film memtranstor have been investigated. These findings demonstrate the potential of the PZT/FeGa thin film memtranstor for non-volatile memory applications., Comment: 10 pages, 4 figures

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features as input to the model results in the loss of fine-grained information within the evidence. Secondly, a gap exists between the feature extraction of evidence and the question, which hinders the model from effectively extracting critical features from the evidence based on the given question. We propose a two-stage framework for evidence retrieval and question-answering to alleviate these issues. First and foremost, we propose a progressive evidence refinement strategy for selecting crucial evidence. This strategy employs an iterative evidence retrieval approach to uncover the logical sequence among the evidence pieces. It incorporates two rounds of filtering to optimize the solution space, thus further ensuring temporal efficiency. Subsequently, we introduce a semi-supervised contrastive learning training strategy based on negative samples to expand the scope of the question domain, allowing for a more thorough exploration of latent knowledge within known samples. Finally, in order to mitigate the loss of fine-grained information, we devise a multi-turn retrieval and question-answering strategy to handle multimodal inputs. This strategy involves incorporating multimodal evidence directly into the model as part of the historical dialogue and question. Meanwhile, we leverage a cross-modal attention mechanism to capture the underlying connections between the evidence and the question, and the answer is generated through a decoding generation approach. We validate the model's effectiveness through extensive experiments, achieving outstanding performance on WebQA and MultimodelQA benchmark tests.

Controlling the in-band co-polarization scattering of the antenna while maintaining its radiation performance is crucial for the low observable platform. Thus, this paper studies the in-band co-polarization scattering beam scanning of antenna arrays. Firstly, the regulation method of antenna scattering is analyzed theoretically, concluding that the amplitude and phase of the antenna's scattering field can be regulated by changing the load impedance. Subsequently, PIN diodes are implemented to control the load impedance of the antenna. Consequently, the scattering of the antenna, ensuring that the antenna's scattering meets the condition of equal amplitude and a phase difference of 180{\deg} when the PIN diode switches, thereby realizing scattering beam scanning. Moreover, by introducing an additional pre-phase, the inherent symmetric dual-beam issue observed in traditional 1-bit reconfigurable structures is overcome, achieving single-beam scanning of the scattering. Finally, a 1{\times}16 linear antenna array is designed and fabricated, which operates at 6 GHz with radiation gain of 16.3 dBi. The scattering beams of the designed array can point to arbitrary angles within 45{\deg}, significantly reducing the in-band co-polarization backward radar cross section. The measured results align well with the simulated ones.

Event Relation Extraction (ERE) aims to extract multiple kinds of relations among events in texts. However, existing methods singly categorize event relations as different classes, which are inadequately capturing the intrinsic semantics of these relations. To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations. Specifically, ProtoEM extracts event relations in a two-step manner, i.e., prototype representing and prototype matching. In the first step, to capture the connotations of different event relations, ProtoEM utilizes examples to represent the prototypes corresponding to these relations. Subsequently, to capture the interdependence among event relations, it constructs a dependency graph for the prototypes corresponding to these relations and utilized a Graph Neural Network (GNN)-based module for modeling. In the second step, it obtains the representations of new event pairs and calculates their similarity with those prototypes obtained in the first step to evaluate which types of event relations they belong to. Experimental results on the MAVEN-ERE dataset demonstrate that the proposed ProtoEM framework can effectively represent the prototypes of event relations and further obtain a significant improvement over baseline models., Comment: Work in progress

This paper considers a type of incremental aggregated gradient (IAG) method for large-scale distributed optimization. The IAG method is well suited for the parameter server architecture as the latter can easily aggregate potentially staled gradients contributed by workers. Although the convergence of IAG in the case of deterministic gradient is well known, there are only a few results for the case of its stochastic variant based on streaming data. Considering strongly convex optimization, this paper shows that the streaming IAG method achieves linear speedup when the workers are updating frequently enough, even if the data sample distribution across workers are heterogeneous. We show that the expected squared distance to optimal solution decays at O((1+T)/(nt)), where $n$ is the number of workers, t is the iteration number, and T/n is the update frequency of workers. Our analysis involves careful treatments of the conditional expectations with staled gradients and a recursive system with both delayed and noise terms, which are new to the analysis of IAG-type algorithms. Numerical results are presented to verify our findings., Comment: 8 pages, 3 figures

An all-optical method for directly reconstructing the spectral phase of isolated attosecond pulse (IAP) has been proposed recently [New J. Phys. 25, 083003 (2023)]. This method is based on the high-harmonic generation (HHG) streaking spectra generated by an IAP and a time-delayed intense infrared (IR) laser, which can be accurately simulated by an extended quantitative rescattering model. Here we extend the retrieval algorithm in this method to successfully retrieve the spectral phase of an shaped IAP, which has a spectral minimum, a phase jump about $\pi$, and a "split" temporal profile. We then reconstruct the carrier-envelope phase of IR laser from HHG streaking spectra. And we finally discuss the retrieval of the phase of high harmonics by the intense IR laser alone using the Fourier transform of HHG streaking spectra.

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website., Comment: Technical Report; 65 pages, 34 figures, 24 tables; Code at https://github.com/ldkong1205/RoboDepth

In this big data era, the use of large dataset in conjunction with machine learning (ML) has been increasingly popular in both industry and academia. In recent times, the field of materials science is also undergoing a big data revolution, with large database and repositories appearing everywhere. Traditionally, materials science is a trial-and-error field, in both the computational and experimental departments. With the advent of machine learning-based techniques, there has been a paradigm shift: materials can now be screened quickly using ML models and even generated based on materials with similar properties; ML has also quietly infiltrated many sub-disciplinary under materials science. However, ML remains relatively new to the field and is expanding its wing quickly. There are a plethora of readily-available big data architectures and abundance of ML models and software; The call to integrate all these elements in a comprehensive research procedure is becoming an important direction of material science research. In this review, we attempt to provide an introduction and reference of ML to materials scientists, covering as much as possible the commonly used methods and applications, and discussing the future possibilities., Comment: 60 pages; 22 figures