Search

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So the generated images do not consistently align with human expectations, especially in complex scenarios involving multiple objects and relationships. In this paper, we introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations. This enhancement is particularly notable in maintaining precise correspondence in scenarios involving multiple relationships. To address the challenges posed by low-quality annotated datasets like Visual Genome, we have manually curated a highly clean, multi-relational scene graph-image paired dataset MultiRels. Furthermore, we design three metrics derived from GPT-4V to effectively and thoroughly measure the correspondence between images and scene graphs. Both qualitative and quantitative results validate the efficacy of our approach in controlling the correspondence in multiple relationships.

Diffusion Models (DMs) have exhibited superior performance in generating high-quality and diverse images. However, this exceptional performance comes at the cost of expensive architectural design, particularly due to the attention module heavily used in leading models. Existing works mainly adopt a retraining process to enhance DM efficiency. This is computationally expensive and not very scalable. To this end, we introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of redundant tokens, without the need for any retraining. Specifically, for single-denoising-step pruning, we develop a novel ranking algorithm, Generalized Weighted Page Rank (G-WPR), to identify redundant tokens, and a similarity-based recovery method to restore tokens for the convolution operation. In addition, we propose a Denoising-Steps-Aware Pruning (DSAP) approach to adjust the pruning budget across different denoising timesteps for better generation quality. Extensive evaluations show that AT-EDM performs favorably against prior art in terms of efficiency (e.g., 38.8% FLOPs saving and up to 1.53x speed-up over Stable Diffusion XL) while maintaining nearly the same FID and CLIP scores as the full model. Project webpage: https://atedm.github.io., Comment: Accepted to IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models. Recognizing the unique challenges posed by video's spatiotemporal nature, our method introduces Motion Embeddings, a set of explicit, temporally coherent one-dimensional embeddings derived from a given video. These embeddings are designed to integrate seamlessly with the temporal transformer modules of video diffusion models, modulating self-attention computations across frames without compromising spatial integrity. Our approach offers a compact and efficient solution to motion representation and enables complex manipulations of motion characteristics through vector arithmetic in the embedding space. Furthermore, we identify the Temporal Discrepancy in video generative models, which refers to variations in how different motion modules process temporal relationships between frames. We leverage this understanding to optimize the integration of our motion embeddings. Our contributions include the introduction of a tailored motion embedding for customization tasks, insights into the temporal processing differences in video models, and a demonstration of the practical advantages and effectiveness of our method through extensive experiments., Comment: Project Page: https://wileewang.github.io/MotionInversion/

Decentralized Storage Network (DSN) is an emerging technology that challenges traditional cloud-based storage systems by consolidating storage capacities from independent providers and coordinating to provide decentralized storage and retrieval services. However, current DSNs face several challenges associated with data privacy and efficiency of the proof systems. To address these issues, we propose FileDES (\uline{D}ecentralized \uline{E}ncrypted \uline{S}torage), which incorporates three essential elements: privacy preservation, scalable storage proof, and batch verification. FileDES provides encrypted data storage while maintaining data availability, with a scalable Proof of Encrypted Storage (PoES) algorithm that is resilient to Sybil and Generation attacks. Additionally, we introduce a rollup-based batch verification approach to simultaneously verify multiple files using publicly verifiable succinct proofs. We conducted a comparative evaluation on FileDES, Filecoin, Storj and Sia under various conditions, including a WAN composed of up to 120 geographically dispersed nodes. Our protocol outperforms the others in terms of proof generation/verification efficiency, storage costs, and scalability., Comment: 10 pages, 8 figures, 1 table. Accepted by 2024 IEEE INFOCOM

The growing demand for personalized decision-making has led to a surge of interest in estimating the Conditional Average Treatment Effect (CATE). The intersection of machine learning and causal inference has yielded various effective CATE estimators. However, deploying these estimators in practice is often hindered by the absence of counterfactual labels, making it challenging to select the desirable CATE estimator using conventional model selection procedures like cross-validation. Existing approaches for CATE estimator selection, such as plug-in and pseudo-outcome metrics, face two inherent challenges. Firstly, they are required to determine the metric form and the underlying machine learning models for fitting nuisance parameters or plug-in learners. Secondly, they lack a specific focus on selecting a robust estimator. To address these challenges, this paper introduces a novel approach, the Distributionally Robust Metric (DRM), for CATE estimator selection. The proposed DRM not only eliminates the need to fit additional models but also excels at selecting a robust CATE estimator. Experimental studies demonstrate the efficacy of the DRM method, showcasing its consistent effectiveness in identifying superior estimators while mitigating the risk of selecting inferior ones.

Consumer credit services offered by e-commerce platforms provide customers with convenient loan access during shopping and have the potential to stimulate sales. To understand the causal impact of credit lines on spending, previous studies have employed causal estimators, based on direct regression (DR), inverse propensity weighting (IPW), and double machine learning (DML) to estimate the treatment effect. However, these estimators do not consider the notion that an individual's spending can be understood and represented as a distribution, which captures the range and pattern of amounts spent across different orders. By disregarding the outcome as a distribution, valuable insights embedded within the outcome distribution might be overlooked. This paper develops a distribution-valued estimator framework that extends existing real-valued DR-, IPW-, and DML-based estimators to distribution-valued estimators within Rubin's causal framework. We establish their consistency and apply them to a real dataset from a large e-commerce platform. Our findings reveal that credit lines positively influence spending across all quantiles; however, as credit lines increase, consumers allocate more to luxuries (higher quantiles) than necessities (lower quantiles).

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object generation. This work illuminates the fundamental reasons for such misalignment, pinpointing issues related to low attention activation scores and mask overlaps. While previous research efforts have individually tackled these issues, we assert that a holistic approach is paramount. Thus, we propose two novel objectives, the Separate loss and the Enhance loss, that reduce object mask overlaps and maximize attention scores, respectively. Our method diverges from conventional test-time-adaptation techniques, focusing on finetuning critical parameters, which enhances scalability and generalizability. Comprehensive evaluations demonstrate the superior performance of our model in terms of image realism, text-image alignment, and adaptability, notably outperforming prominent baselines. Ultimately, this research paves the way for T2I diffusion models with enhanced compositional capacities and broader applicability.

The advent of predictive methodologies has catalyzed the emergence of data-driven decision support across various domains. However, developing models capable of effectively handling input time series data presents an enduring challenge. This study presents novel preference learning approaches to multiple criteria sorting problems in the presence of temporal criteria. We first formulate a convex quadratic programming model characterized by fixed time discount factors, operating within a regularization framework. To enhance scalability and accommodate learnable time discount factors, we introduce a novel monotonic Recurrent Neural Network (mRNN). It is designed to capture the evolving dynamics of preferences over time while upholding critical properties inherent to MCS problems, including criteria monotonicity, preference independence, and the natural ordering of classes. The proposed mRNN can describe the preference dynamics by depicting marginal value functions and personalized time discount factors along with time, effectively amalgamating the interpretability of traditional MCS methods with the predictive potential offered by deep preference learning models. Comprehensive assessments of the proposed models are conducted, encompassing synthetic data scenarios and a real-case study centered on classifying valuable users within a mobile gaming app based on their historical in-app behavioral sequences. Empirical findings underscore the notable performance improvements achieved by the proposed models when compared to a spectrum of baseline methods, spanning machine learning, deep learning, and conventional multiple criteria sorting approaches.

Time series forecasting is prevalent in various real-world applications. Despite the promising results of deep learning models in time series forecasting, especially the Recurrent Neural Networks (RNNs), the explanations of time series models, which are critical in high-stakes applications, have received little attention. In this paper, we propose a Decomposition-based Linear Explainable LSTM (DeLELSTM) to improve the interpretability of LSTM. Conventionally, the interpretability of RNNs only concentrates on the variable importance and time importance. We additionally distinguish between the instantaneous influence of new coming data and the long-term effects of historical data. Specifically, DeLELSTM consists of two components, i.e., standard LSTM and tensorized LSTM. The tensorized LSTM assigns each variable with a unique hidden state making up a matrix $\mathbf{h}_t$, and the standard LSTM models all the variables with a shared hidden state $\mathbf{H}_t$. By decomposing the $\mathbf{H}_t$ into the linear combination of past information $\mathbf{h}_{t-1}$ and the fresh information $\mathbf{h}_{t}-\mathbf{h}_{t-1}$, we can get the instantaneous influence and the long-term effect of each variable. In addition, the advantage of linear regression also makes the explanation transparent and clear. We demonstrate the effectiveness and interpretability of DeLELSTM on three empirical datasets. Extensive experiments show that the proposed method achieves competitive performance against the baseline methods and provides a reliable explanation relative to domain knowledge.

We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution builds on the StyleGAN3 architecture, with a shared backbone and modality-specific branches in the last layers of the synthesis network, and we propose per-modality fidelity discriminators and a cross-modality consistency discriminator. In experiments on the Stanford2D3D dataset, we demonstrate realistic and consistent generation of RGB, depth, and normal images. We also show a training recipe to easily extend our pretrained model on a new domain, even with a few pairwise data. We further evaluate the use of synthetically generated RGB and depth pairs for training or fine-tuning depth estimators. Code will be available at https://github.com/jessemelpolio/MultimodalGAN., Comment: In review

Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g.,depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect alignment between the text and extra conditions. If this alignment is not satisfied, the final output could be either dominated by one condition, or ambiguity may arise, failing to meet user expectations. To address this issue, we present a training free approach called Text-Anchored Score Composition (TASC) to further improve the controllability of existing models when provided with partially aligned conditions. The TASC firstly separates conditions based on pair relationships, computing the result individually for each pair. This ensures that each pair no longer has conflicting conditions. Then we propose an attention realignment operation to realign these independently calculated results via a cross-attention mechanism to avoid new conflicts when combining them back. Both qualitative and quantitative results demonstrate the effectiveness of our approach in handling unaligned conditions, which performs favorably against recent methods and more importantly adds flexibility to the controllable image generation process. Our code will be available at: https://github.com/EnVision-Research/Decompose-and-Realign.

Multivariate sequential data collected in practice often exhibit temporal irregularities, including nonuniform time intervals and component misalignment. However, if uneven spacing and asynchrony are endogenous characteristics of the data rather than a result of insufficient observation, the information content of these irregularities plays a defining role in characterizing the multivariate dependence structure. Existing approaches for probabilistic forecasting either overlook the resulting statistical heterogeneities, are susceptible to imputation biases, or impose parametric assumptions on the data distribution. This paper proposes an end-to-end solution that overcomes these limitations by allowing the observation arrival times to play the central role of model construction, which is at the core of temporal irregularities. To acknowledge temporal irregularities, we first enable unique hidden states for components so that the arrival times can dictate when, how, and which hidden states to update. We then develop a conditional flow representation to non-parametrically represent the data distribution, which is typically non-Gaussian, and supervise this representation by carefully factorizing the log-likelihood objective to select conditional information that facilitates capturing time variation and path dependency. The broad applicability and superiority of the proposed solution are confirmed by comparing it with existing approaches through ablation studies and testing on real-world datasets.

We present a lightweighted neural PDE representation to discover the hidden structure and predict the solution of different nonlinear PDEs. Our key idea is to leverage the prior of ``translational similarity'' of numerical PDE differential operators to drastically reduce the scale of learning model and training data. We implemented three central network components, including a neural functional convolution operator, a Picard forward iterative procedure, and an adjoint backward gradient calculator. Our novel paradigm fully leverages the multifaceted priors that stem from the sparse and smooth nature of the physical PDE solution manifold and the various mature numerical techniques such as adjoint solver, linearization, and iterative procedure to accelerate the computation. We demonstrate the efficacy of our method by robustly discovering the model and accurately predicting the solutions of various types of PDEs with small-scale networks and training sets. We highlight that all the PDE examples we showed were trained with up to 8 data samples and within 325 network parameters., Comment: 10 pages of main text, 7 pages of appendix, 7 figures in main text

Large-scale text-to-image generative models have shown their remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is hard for users to come up with a perfect text prompt that accurately describes every visual detail in the input image. Second, while existing models can introduce desirable changes in certain regions, they often dramatically alter the input content and introduce unexpected changes in unwanted regions. In this work, we propose pix2pix-zero, an image-to-image translation method that can preserve the content of the original image without manual prompting. We first automatically discover editing directions that reflect desired edits in the text embedding space. To preserve the general content structure after editing, we further propose cross-attention guidance, which aims to retain the cross-attention maps of the input image throughout the diffusion process. In addition, our method does not need additional training for these edits and can directly use the existing pre-trained text-to-image diffusion model. We conduct extensive experiments and show that our method outperforms existing and concurrent works for both real and synthetic image editing., Comment: website: https://pix2pixzero.github.io/

Deciphering cell type heterogeneity is crucial for systematically understanding tissue homeostasis and its dysregulation in diseases. Computational deconvolution is an efficient approach estimating cell type abundances from a variety of omics data. Despite significant methodological progress in computational deconvolution in recent years, challenges are still outstanding. Here we enlist four significant challenges related to computational deconvolution, from the quality of the reference data, generation of ground truth data, limitations of computational methodologies, and benchmarking design and implementation. Finally, we make recommendations on reference data generation, new directions of computational methodologies and strategies to promote rigorous benchmarking.

We introduce a new method for diverse foreground generation with explicit control over various factors. Existing image inpainting based foreground generation methods often struggle to generate diverse results and rarely allow users to explicitly control specific factors of variation (e.g., varying the facial identity or expression for face inpainting results). We leverage contrastive learning with latent codes to generate diverse foreground results for the same masked input. Specifically, we define two sets of latent codes, where one controls a pre-defined factor (``known''), and the other controls the remaining factors (``unknown''). The sampled latent codes from the two sets jointly bi-modulate the convolution kernels to guide the generator to synthesize diverse results. Experiments demonstrate the superiority of our method over state-of-the-arts in result diversity and generation controllability., Comment: ECCV 2022

3D-controllable portrait synthesis has significantly advanced, thanks to breakthroughs in generative adversarial networks (GANs). However, it is still challenging to manipulate existing face images with precise 3D control. While concatenating GAN inversion and a 3D-aware, noise-to-image GAN is a straight-forward solution, it is inefficient and may lead to noticeable drop in editing quality. To fill this gap, we propose 3D-FM GAN, a novel conditional GAN framework designed specifically for 3D-controllable face manipulation, and does not require any tuning after the end-to-end learning phase. By carefully encoding both the input face image and a physically-based rendering of 3D edits into a StyleGAN's latent spaces, our image generator provides high-quality, identity-preserved, 3D-controllable face manipulation. To effectively learn such novel framework, we develop two essential training strategies and a novel multiplicative co-modulation architecture that improves significantly upon naive schemes. With extensive evaluations, we show that our method outperforms the prior arts on various tasks, with better editability, stronger identity preservation, and higher photo-realism. In addition, we demonstrate a better generalizability of our design on large pose editing and out-of-domain images., Comment: Accepted to ECCV2022. Project webpage: https://lychenyoko.github.io/3D-FM-GAN-Webpage/

In the long pursuit of smart robotics, it has been envisioned to empower robots with human-like senses, especially vision and touch. While tremendous progress has been made in image sensors and computer vision over the past decades, the tactile sense abilities are lagging behind due to the lack of large-scale flexible tactile sensor array with high sensitivity, high spatial resolution, and fast response. In this work, we have demonstrated a 64x64 flexible tactile sensor array with a record-high spatial resolution of 0.9 mm (equivalently 28.2 pixels per inch), by integrating a high-performance piezoresistive film (PRF) with a large-area active matrix of carbon nanotube thin-film transistors. PRF with self-formed microstructures exhibited high pressure-sensitivity of ~385 kPa-1 for MWCNTs concentration of 6%, while the 14% one exhibited fast response time of ~3 ms, good linearity, broad detection range beyond 1400 kPa, and excellent cyclability over 3000 cycles. Using this fully integrated tactile sensor array, the footprint maps of an artificial honeybee were clearly identified. Furthermore, we hardware-implemented a smart tactile system by integrating the PRF-based sensor array with a memristor-based computing-in-memory chip to record and recognize handwritten digits and Chinese calligraphy, achieving high classification accuracies of 98.8% and 97.3% in hardware, respectively. The integration of sensor networks with deep learning hardware may enable edge or near-sensor computing with significantly reduced power consumption and latency. Our work could pave the road to building large-scale intelligent sensor networks for next-generation smart robotics., Comment: Correction in Methods: The weight ratio of TPU:DMF was set to be 1:5

In this work, we propose a complete framework that generates visual art. Unlike previous stylization methods that are not flexible with style parameters (i.e., they allow stylization with only one style image, a single stylization text or stylization of a content image from a certain domain), our method has no such restriction. In addition, we implement an improved version that can generate a wide range of results with varying degrees of detail, style and structure, with a boost in generation speed. To further enhance the results, we insert an artistic super-resolution module in the generative pipeline. This module will bring additional details such as patterns specific to painters, slight brush marks, and so on.

Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the "invertibility" of different image segments and project each segment into a latent layer. Easier regions can be inverted into an earlier layer in the generator's latent space, while more challenging regions can be inverted into a later feature space. Experiments show that our method obtains better inversion results compared to the recent approaches on complex categories, while maintaining downstream editability. Please refer to our project page at https://www.cs.cmu.edu/~SAMInversion., Comment: CVPR 2022. Github: https://github.com/adobe-research/sam_inversion Website: https://www.cs.cmu.edu/~SAMInversion

Spatial transcriptomics (ST) has advanced significantly in the last few years. Such advancement comes with the urgent need for novel computational methods to handle the unique challenges of ST data analysis. Many artificial intelligence (AI) methods have been developed to utilize various machine learning and deep learning techniques for computational ST analysis. This review provides a comprehensive and up-to-date survey of current AI methods for ST analysis.

Recently developed technologies to generate single-cell genomic data have made a revolutionary impact in the field of biology. Multi-omics assays offer even greater opportunities to understand cellular states and biological processes. However, the problem of integrating different -omics data with very different dimensionality and statistical properties remains quite challenging. A growing body of computational tools are being developed for this task, leveraging ideas ranging from machine translation to the theory of networks and representing a new frontier on the interface of biology and data science. Our goal in this review paper is to provide a comprehensive, up-to-date survey of computational techniques for the integration of multi-omics and alignment of multiple modalities of genomics data in the single cell research field., Comment: 26 pages, 4 figures

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy manipulation of a specific object in the scene. Experiments show that our approach can generate high quality images in high resolution while having flexibility of object-level control by using class-specific generators., Comment: ICCV 2021

Intercellular heterogeneity is a major obstacle to successful precision medicine. Single-cell RNA sequencing (scRNA-seq) technology has enabled in-depth analysis of intercellular heterogeneity in various diseases. However, its full potential for precision medicine has yet to be reached. Towards this, we propose a new drug recommendation system called: A Single-cell Guided Pipeline to Aid Repurposing of Drugs (ASGARD). ASGARD defines a novel drug score predicting drugs by considering all cell clusters to address the intercellular heterogeneity within each patient. We tested ASGARD on multiple diseases, including breast cancer, acute lymphoblastic leukemia, and coronavirus disease 2019 (COVID-19). On single-drug therapy, ASGARD shows significantly better average accuracy (AUC of 0.92) compared to two other bulk-cell-based drug repurposing methods (AUC of 0.80 and 0.76). It is also considerably better (AUC of 0.82) than other cell cluster level predicting methods (AUC of 0.67 and 0.55). In addition, ASGARD is also validated by the drug response prediction method TRANSACT with Triple-Negative-Breast-Cancer patient samples. Many top-ranked drugs are either approved by FDA or in clinical trials treating corresponding diseases. In silico cell-type specific drop-out experiments using triple-negative breast cancers show the importance of T cells in the tumor microenvironment in affecting drug predictions. In conclusion, ASGARD is a promising drug repurposing recommendation tool guided by single-cell RNA-seq for personalized medicine. ASGARD is free for educational use at https://github.com/lanagarmire/ASGARD.