Search

The rapid development of diffusion models has triggered diverse applications. Identity-preserving text-to-image generation (ID-T2I) particularly has received significant attention due to its wide range of application scenarios like AI portrait and advertising. While existing ID-T2I methods have demonstrated impressive results, several key challenges remain: (1) It is hard to maintain the identity characteristics of reference portraits accurately, (2) The generated images lack aesthetic appeal especially while enforcing identity retention, and (3) There is a limitation that cannot be compatible with LoRA-based and Adapter-based methods simultaneously. To address these issues, we present \textbf{ID-Aligner}, a general feedback learning framework to enhance ID-T2I performance. To resolve identity features lost, we introduce identity consistency reward fine-tuning to utilize the feedback from face detection and recognition models to improve generated identity preservation. Furthermore, we propose identity aesthetic reward fine-tuning leveraging rewards from human-annotated preference data and automatically constructed feedback on character structure generation to provide aesthetic tuning signals. Thanks to its universal feedback fine-tuning framework, our method can be readily applied to both LoRA and Adapter models, achieving consistent performance gains. Extensive experiments on SD1.5 and SDXL diffusion models validate the effectiveness of our approach. \textbf{Project Page: \url{https://idaligner.github.io/}}

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation; and ii) ODE Trajectory Reformulation. However, these approaches suffer from severe performance degradation or domain shifts. To address these limitations, we propose Hyper-SD, a novel framework that synergistically amalgamates the advantages of ODE Trajectory Preservation and Reformulation, while maintaining near-lossless performance during step compression. Firstly, we introduce Trajectory Segmented Consistency Distillation to progressively perform consistent distillation within pre-defined time-step segments, which facilitates the preservation of the original ODE trajectory from a higher-order perspective. Secondly, we incorporate human feedback learning to boost the performance of the model in a low-step regime and mitigate the performance loss incurred by the distillation process. Thirdly, we integrate score distillation to further improve the low-step generation capability of the model and offer the first attempt to leverage a unified LoRA to support the inference process at all steps. Extensive experiments and user studies demonstrate that Hyper-SD achieves SOTA performance from 1 to 8 inference steps for both SDXL and SD1.5. For example, Hyper-SDXL surpasses SDXL-Lightning by +0.68 in CLIP Score and +0.51 in Aes Score in the 1-step inference.

Motivated by recent development of mean-field systems with common noise, this paper establishes Ito's formula for flows of conditional probability measures under a common filtration associated with general semimartingales. This generalizes existing works on flows of conditional measures on Ito processes and flows of deterministic measure on general semimartingales. The key technical components involve constructing conditional independent copies and establishing the equivalence between stochastic integrals with respect to the conditional law of semimartingales and the conditional expectation of stochastic integrals with respect to copies of semimartingales. Ito's formula is then established for cylindrical functions through conditional independent copies, and extended to the general case through function approximations.

Diffusion models have revolutionized the field of image generation, leading to the proliferation of high-quality models and diverse downstream applications. However, despite these significant advancements, the current competitive solutions still suffer from several limitations, including inferior visual quality, a lack of aesthetic appeal, and inefficient inference, without a comprehensive solution in sight. To address these challenges, we present UniFL, a unified framework that leverages feedback learning to enhance diffusion models comprehensively. UniFL stands out as a universal, effective, and generalizable solution applicable to various diffusion models, such as SD1.5 and SDXL. Notably, UniFL incorporates three key components: perceptual feedback learning, which enhances visual quality; decoupled feedback learning, which improves aesthetic appeal; and adversarial feedback learning, which optimizes inference speed. In-depth experiments and extensive user studies validate the superior performance of our proposed method in enhancing both the quality of generated models and their acceleration. For instance, UniFL surpasses ImageReward by 17% user preference in terms of generation quality and outperforms LCM and SDXL Turbo by 57% and 20% in 4-step inference. Moreover, we have verified the efficacy of our approach in downstream tasks, including Lora, ControlNet, and AnimateDiff.

We delve into pseudo-labeling for semi-supervised monocular 3D object detection (SSM3OD) and discover two primary issues: a misalignment between the prediction quality of 3D and 2D attributes and the tendency of depth supervision derived from pseudo-labels to be noisy, leading to significant optimization conflicts with other reliable forms of supervision. We introduce a novel decoupled pseudo-labeling (DPL) approach for SSM3OD. Our approach features a Decoupled Pseudo-label Generation (DPG) module, designed to efficiently generate pseudo-labels by separately processing 2D and 3D attributes. This module incorporates a unique homography-based method for identifying dependable pseudo-labels in BEV space, specifically for 3D attributes. Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients. This dual decoupling strategy-at both the pseudo-label generation and gradient levels-significantly improves the utilization of pseudo-labels in SSM3OD. Our comprehensive experiments on the KITTI benchmark demonstrate the superiority of our method over existing approaches., Comment: To appear in CVPR2024

We propose and demonstrate an on-chip 1*N power splitter based on topological photonic crystal (TPC) on a monolithic silicon photonic platform. Benefiting from the valley-locked propagation mode at the interface of TPCs with different topological phases, the proposed power splitter has negligible backscattering around the sharp bendings and good robustness to fabrication defects, which therefore enable lower insertion loss, better uniformity, and more compact footprint than the conventional designs. For the fabricated 1*2 (8) power splitter, the uniformity among the output ports is below 0.35 (0.65) dB and the maximum insertion loss is 0.38 (0.58) dB with compact footprint of 5*5 um2 (10*12 um2) within a bandwidth of 70 nm. In addition, the topological power splitter only requires simple configurations of TPCs with different topological phases, which is more reliable in design and fabrication compared with the conventional designs., Comment: 8 pages,4 figures

An emerging line of work has sought to generate plausible imagery from touch. Existing approaches, however, tackle only narrow aspects of the visuo-tactile synthesis problem, and lag significantly behind the quality of cross-modal synthesis methods in other domains. We draw on recent advances in latent diffusion to create a model for synthesizing images from tactile signals (and vice versa) and apply it to a number of visuo-tactile synthesis tasks. Using this model, we significantly outperform prior work on the tactile-driven stylization problem, i.e., manipulating an image to match a touch signal, and we are the first to successfully generate images from touch without additional sources of information about the scene. We also successfully use our model to address two novel synthesis problems: generating images that do not contain the touch sensor or the hand holding it, and estimating an image's shading from its reflectance and touch., Comment: ICCV 2023; Project site: https://fredfyyang.github.io/vision-from-touch/

Internet-based services have seen remarkable success, generating vast amounts of monitored key performance indicators (KPIs) as univariate or multivariate time series. Monitoring and analyzing these time series are crucial for researchers, service operators, and on-call engineers to detect outliers or anomalies indicating service failures or significant events. Numerous advanced anomaly detection methods have emerged to address availability and performance issues. This review offers a comprehensive overview of time series anomaly detection in Artificial Intelligence for IT operations (AIOps), which uses AI capabilities to automate and optimize operational workflows. Additionally, it explores future directions for real-world and next-generation time-series anomaly detection based on recent advancements.

We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training inefficiency; (2) DETR-based detectors lack deterministic correspondence between the input query and its prediction output, which hinders the applicability of the consistency-based regularization widely used in current SSOD methods. We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector, to tackle these problems. Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage. Besides, we introduce a Crossview Query Consistency method to learn the semantic feature invariance of object queries from different views while avoiding the need to find deterministic query correspondence. Furthermore, we propose a Cost-based Pseudo Label Mining module to dynamically mine more pseudo boxes based on the matching cost of pseudo ground truth bounding boxes for consistency training. Extensive experiments on all SSOD settings of both COCO and Pascal VOC benchmark datasets show that our Semi-DETR method outperforms all state-of-the-art methods by clear margins. The PaddlePaddle version code1 is at https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det/semi_detr., Comment: CVPR2023

In this paper, we propose several approaches to learn the optimal population-dependent controls in order to solve mean field control problems (MFC). Such policies enable us to solve MFC problems with forms of common noises at a level of generality that was not covered by existing methods. We analyze rigorously the theoretical convergence of the proposed approximation algorithms. Of particular interest for its simplicity of implementation is the $N$-particle approximation. The effectiveness and the flexibility of our algorithms is supported by numerical experiments comparing several combinations of distribution approximation techniques and neural network architectures. We use three different benchmark problems from the literature: a systemic risk model, a price impact model, and a crowd motion model. We first show that our proposed algorithms converge to the correct solution in an explicitly solvable MFC problem. Then, we show that population-dependent controls outperform state-dependent controls. Along the way, we show that specific neural network architectures can improve the learning further., Comment: 23 pages, 6 figures

This paper studies the central planner's decision making on behalf of a group of members with diverse discount rates. In the context of optimal stopping, we work with a smooth aggregation preference to incorporate all heterogeneous discount rates with an attitude function that reflects the aggregation rule in the same spirit of ambiguity aversion in the smooth ambiguity preference proposed in Klibanoff et al.(2005). The optimal stopping problem renders to be time inconsistent, for which we develop an iterative approach using consistent planning and characterize all time-consistent equilibria as fixed points of an operator in the setting of one-dimensional diffusion processes. We provide some sufficient conditions on both the underlying models and the attitude function such that the smallest equilibrium attains the optimal equilibrium in which the attitude function becomes equivalent to the linear aggregation rule as of diversity neutral. In addition, we show that the optimal equilibrium is a weak equilibrium in the existing literature. When the sufficient condition of the attitude function is violated, we can illustrate by various examples that the characterization of the optimal equilibrium may differ significantly from some existing results for an individual agent., Comment: Typos are corrected. A new section on the connection between optimal mild equilibrium and weak equilibrium is added

In this paper, a new speech feature fusion method is proposed for speaker recognition on the basis of the cross gate parallel convolutional neural network (CG-PCNN). The Mel filter bank features (MFBFs) of different frequency resolutions can be extracted from each speech frame of a speaker's speech by several Mel filter banks, where the numbers of the triangular filters in the Mel filter banks are different. Due to the frequency resolutions of these MFBFs are different, there are some complementaries for these MFBFs. The CG-PCNN is utilized to extract the deep features from these MFBFs, which applies a cross gate mechanism to capture the complementaries for improving the performance of the speaker recognition system. Then, the fusion feature can be obtained by concatenating these deep features for speaker recognition. The experimental results show that the speaker recognition system with the proposed speech feature fusion method is effective, and marginally outperforms the existing state-of-the-art systems.