Searcharxiv⌕ Search

arXiv subjects

Chen Zhao

Publications and source records attributed to Chen Zhao.

At least 289 records · Page 16Linked to original sources
arXiv2023

HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation

In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models. Recent progress (Magic3D) in text-to-3D has shown that employing high-resolution (e.g., 512 x 512) renderings can lead to the production of high-quality 3D models using latent diffusion priors. To enable rendering at even higher resolutions, which has the potential to further augment the quality and detail of the models, we propose a novel approach that combines multiple noise estimation processes with a pretrained 2D diffusion prior. Distinct from the Bar-Tal et al.s' study which binds multiple denoised results to generate images from texts, our approach integrates the computation of scoring distillation losses such as SDS loss and VSD loss which are essential techniques for the 3D content generation with 2D diffusion priors. We experimentally evaluated the proposed approach. The results show that the proposed approach can generate high-quality details compared to the baselines.

cs.CV↗
arXiv2023

Towards Fair Disentangled Online Learning for Changing Environments

In the problem of online learning for changing environments, data are sequentially received one after another over time, and their distribution assumptions may vary frequently. Although existing methods demonstrate the effectiveness of their learning algorithms by providing a tight bound on either dynamic regret or adaptive regret, most of them completely ignore learning with model fairness, defined as the statistical parity across different sub-population (e.g., race and gender). Another drawback is that when adapting to a new environment, an online learner needs to update model parameters with a global change, which is costly and inefficient. Inspired by the sparse mechanism shift hypothesis, we claim that changing environments in online learning can be attributed to partial changes in learned parameters that are specific to environments and the rest remain invariant to changing environments. To this end, in this paper, we propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations, an environment-invariant semantic factor and an environment-specific variation factor. The semantic factor is further used for fair prediction under a group fairness constraint. To evaluate the sequence of model parameters generated by the learner, a novel regret is proposed in which it takes a mixed form of dynamic and static regret metrics followed by a fairness-aware long-term constraint. The detailed analysis provides theoretical guarantees for loss regret and violation of cumulative fairness constraints. Empirical evaluations on real-world datasets demonstrate our proposed method sequentially outperforms baseline methods in model accuracy and fairness.

cs.LG↗
arXiv2023

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations

Large language models (LLMs) are trained to imitate humans to explain human decisions. However, do LLMs explain themselves? Can they help humans build mental models of how LLMs process different inputs? To answer these questions, we propose to evaluate $\textbf{counterfactual simulatability}$ of natural language explanations: whether an explanation can enable humans to precisely infer the model's outputs on diverse counterfactuals of the explained input. For example, if a model answers "yes" to the input question "Can eagles fly?" with the explanation "all birds can fly", then humans would infer from the explanation that it would also answer "yes" to the counterfactual input "Can penguins fly?". If the explanation is precise, then the model's answer should match humans' expectations. We implemented two metrics based on counterfactual simulatability: precision and generality. We generated diverse counterfactuals automatically using LLMs. We then used these metrics to evaluate state-of-the-art LLMs (e.g., GPT-4) on two tasks: multi-hop factual reasoning and reward modeling. We found that LLM's explanations have low precision and that precision does not correlate with plausibility. Therefore, naively optimizing human approvals (e.g., RLHF) may not be a sufficient solution.

cs.CL↗
arXiv2023

An $L^2$ Dolbeault lemma on higher direct images and its application

Given a proper holomorphic surjective morphism $f:X\rightarrow Y$ from a compact Kähler manifold to a compact Kähler manifold, and a Nakano semipositive holomorphic vector bundle $E$ on $X$, we prove Kollár type vanishing theorems on cohomologies with coefficients in $R^qf_\ast(ω_X(E))\otimes F$, where $F$ is a $k$-positive vector bundle on $Y$. The main inputs in the proof are the deep results on the Nakano semipositivity of the higher direct images due to Berndtsson and Mourougane-Takayama, and an $L^2$-Dolbeault resolution of the higher direct image sheaf $R^qf_\ast(ω_X(E))$, which is of interest in itself.

math.CV↗
arXiv2023

Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation

Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which inspires us to design a data augmentation method to improve the quality of the selected negatives. Moreover, the previous methods only preserve the content consistency via patch-wise contrastive learning in the embedding space, which ignores the domain consistency between the generated images and the real images of the target domain. In this paper, we propose a novel unsupervised image-to-image translation framework based on multi-cropping contrastive learning and domain consistency, called MCDUT. Specifically, we obtain the multi-cropping views via the center-cropping and the random-cropping with the aim of further generating the high-quality negative examples. To constrain the embeddings in the deep feature space, we formulate a new domain consistency loss, which encourages the generated images to be close to the real images in the embedding space of the same domain. Furthermore, we present a dual coordinate attention network by embedding positional information into the channel, which called DCA. We employ the DCA network in the design of generator, which makes the generator capture the horizontal and vertical global information of dependency. In many image-to-image translation tasks, our method achieves state-of-the-art results, and the advantages of our method have been proven through extensive comparison experiments and ablation research.

cs.CV↗
arXiv2023

Just a Glimpse: Rethinking Temporal Information for Video Continual Learning

Class-incremental learning is one of the most important settings for the study of Continual Learning, as it closely resembles real-world application scenarios. With constrained memory sizes, catastrophic forgetting arises as the number of classes/tasks increases. Studying continual learning in the video domain poses even more challenges, as video data contains a large number of frames, which places a higher burden on the replay memory. The current common practice is to sub-sample frames from the video stream and store them in the replay memory. In this paper, we propose SMILE a novel replay mechanism for effective video continual learning based on individual/single frames. Through extensive experimentation, we show that under extreme memory constraints, video diversity plays a more significant role than temporal information. Therefore, our method focuses on learning from a small number of frames that represent a large number of unique videos. On three representative video datasets, Kinetics, UCF101, and ActivityNet, the proposed method achieves state-of-the-art performance, outperforming the previous state-of-the-art by up to 21.49%.

cs.CV↗
arXiv2023

RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations

Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task-specific perturbations, e.g., replacing key question entities or shuffling table columns. To systematically study the robustness of Table QA models, we propose a benchmark called RobuT, which builds upon existing Table QA datasets (WTQ, WikiSQL-Weak, and SQA) and includes human-annotated adversarial perturbations in terms of table header, table content, and question. Our results indicate that both state-of-the-art Table QA models and large language models (e.g., GPT-3) with few-shot learning falter in these adversarial sets. We propose to address this problem by using large language models to generate adversarial examples to enhance training, which significantly improves the robustness of Table QA models. Our data and code is publicly available at https://github.com/yilunzhao/RobuT.

cs.CL↗
arXiv2023

Coronary Artery Semantic Labeling using Edge Attention Graph Matching Network

Coronary artery disease (CAD) is one of the primary causes leading deaths worldwide. The presence of atherosclerotic lesions in coronary arteries is the underlying pathophysiological basis of CAD, and accurate extraction of individual arterial branches using invasive coronary angiography (ICA) is crucial for stenosis detection and CAD diagnosis. We propose an innovative approach called the Edge Attention Graph Matching Network (EAGMN) for coronary artery semantic labeling. By converting the coronary artery semantic segmentation task into a graph node similarity comparison task, identifying the node-to-node correspondence would assign semantic labels for each arterial branch. More specifically, The EAGMN utilizes the association graph constructed from the two individual graphs as input. Experimental results indicate the EAGMN achieved a weighted accuracy of 0.8653, a weighted precision of 0.8656, a weighted recall of 0.8653 and a weighted F1-score of 0.8643. Furthermore, we employ ZORRO to provide interpretability and explainability of the graph matching for artery semantic labeling. These findings highlight the potential of the EAGMN for accurate and efficient coronary artery semantic labeling using ICAs. By leveraging the inherent characteristics of ICAs and incorporating graph matching techniques, our proposed model provides a promising solution for improving CAD diagnosis and treatment

cs.CV↗
arXiv2023

The evolution of k-shell in syndication networks reveals financial performance of venture capital institutions

Venture capital (VC) is a relatively newly emergent industry that is still subject to large uncertainties in China. Therefore, building a robust social network with other VC institutions is a good way to share information, various resources, and benefit from skill and knowledge complementarity to against risks. Strong evidences indicate that better networked VC institutions are of a better financial performance, however, most of previous works overlook the evolution of VC institutions and only focus on some simple topology indicators of the static syndication network, which also neglects higher-order network structure and cannot give a comprehensive evaluation. In this paper, based on VC investment records in the Chinese market, we construct temporal syndication networks between VC institutions year by year. As k-shell decomposition considers higher-order connection patterns, we employ k-shell as an evaluation of the influence of VC institutions in syndication networks. By clustering time series of k-shell values, the VC institutions in China fall into five groups that are quite different from each other on financial performances and investment behaviors. This, in turn, proves the power of our method that only based on proper sequential network properties, we can reveal their financial investment performance. Compared to other network centrality measurements, k-shell is a better indicator that is indicated by a smaller intra-group distance and a larger inter-group distance.

physics.soc-ph↗
arXiv2023

A new method using deep learning to predict the response to cardiac resynchronization therapy

Background. Clinical parameters measured from gated single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) have value in predicting cardiac resynchronization therapy (CRT) patient outcomes, but still show limitations. The purpose of this study is to combine clinical variables, features from electrocardiogram (ECG), and parameters from assessment of cardiac function with polarmaps from gated SPECT MPI through deep learning (DL) to predict CRT response. Methods. 218 patients who underwent rest gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6-month follow up. A DL model was constructed by combining a pre-trained VGG16 module and a multilayer perceptron. Two modalities of data were input to the model: polarmap images from SPECT MPI and tabular data from clinical features and ECG parameters. Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to the VGG16 module to provide explainability for the polarmaps. For comparison, four machine learning (ML) models were trained using only the tabular features. Results. Modeling was performed on 218 patients who underwent CRT implantation with a response rate of 55.5% (n = 121). The DL model demonstrated average AUC (0.83), accuracy (0.73), sensitivity (0.76), and specificity (0.69) surpassing the ML models and guideline criteria. Guideline recommendations presented accuracy (0.53), sensitivity (0.75), and specificity (0.26). Conclusions. The DL model outperformed the ML models, showcasing the additional predictive benefit of utilizing SPECT MPI polarmaps. Incorporating additional patient data directly in the form of medical imagery can improve CRT response prediction.

cs.CV↗
arXiv2023

Large-capacity and Flexible Video Steganography via Invertible Neural Network

Video steganography is the art of unobtrusively concealing secret data in a cover video and then recovering the secret data through a decoding protocol at the receiver end. Although several attempts have been made, most of them are limited to low-capacity and fixed steganography. To rectify these weaknesses, we propose a Large-capacity and Flexible Video Steganography Network (LF-VSN) in this paper. For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN). Our method can hide/recover 7 secret videos in/from 1 cover video with promising performance. For flexibility, we propose a key-controllable scheme, enabling different receivers to recover particular secret videos from the same cover video through specific keys. Moreover, we further improve the flexibility by proposing a scalable strategy in multiple videos hiding, which can hide variable numbers of secret videos in a cover video with a single model and a single training session. Extensive experiments demonstrate that with the significant improvement of the video steganography performance, our proposed LF-VSN has high security, large hiding capacity, and flexibility. The source code is available at https://github.com/MC-E/LF-VSN.

cs.CV↗
arXiv2023

CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data

Integration of heterogeneous and high-dimensional multi-omics data is becoming increasingly important in understanding genetic data. Each omics technique only provides a limited view of the underlying biological process and integrating heterogeneous omics layers simultaneously would lead to a more comprehensive and detailed understanding of diseases and phenotypes. However, one obstacle faced when performing multi-omics data integration is the existence of unpaired multi-omics data due to instrument sensitivity and cost. Studies may fail if certain aspects of the subjects are missing or incomplete. In this paper, we propose a deep learning method for multi-omics integration with incomplete data by Cross-omics Linked unified embedding with Contrastive Learning and Self Attention (CLCLSA). Utilizing complete multi-omics data as supervision, the model employs cross-omics autoencoders to learn the feature representation across different types of biological data. The multi-omics contrastive learning, which is used to maximize the mutual information between different types of omics, is employed before latent feature concatenation. In addition, the feature-level self-attention and omics-level self-attention are employed to dynamically identify the most informative features for multi-omics data integration. Extensive experiments were conducted on four public multi-omics datasets. The experimental results indicated that the proposed CLCLSA outperformed the state-of-the-art approaches for multi-omics data classification using incomplete multi-omics data.

cs.LG↗
arXiv2023

Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization

Temporal action localization (TAL) requires long-form reasoning to predict actions of various durations and complex content. Given limited GPU memory, training TAL end to end (i.e., from videos to predictions) on long videos is a significant challenge. Most methods can only train on pre-extracted features without optimizing them for the localization problem, consequently limiting localization performance. In this work, to extend the potential in TAL networks, we propose a novel end-to-end method Re2TAL, which rewires pretrained video backbones for reversible TAL. Re2TAL builds a backbone with reversible modules, where the input can be recovered from the output such that the bulky intermediate activations can be cleared from memory during training. Instead of designing one single type of reversible module, we propose a network rewiring mechanism, to transform any module with a residual connection to a reversible module without changing any parameters. This provides two benefits: (1) a large variety of reversible networks are easily obtained from existing and even future model designs, and (2) the reversible models require much less training effort as they reuse the pre-trained parameters of their original non-reversible versions. Re2TAL, only using the RGB modality, reaches 37.01% average mAP on ActivityNet-v1.3, a new state-of-the-art record, and mAP 64.9% at tIoU=0.5 on THUMOS-14, outperforming all other RGB-only methods.

cs.CV↗
arXiv2023

Multi-view information fusion using multi-view variational autoencoders to predict proximal femoral strength

The aim of this paper is to design a deep learning-based model to predict proximal femoral strength using multi-view information fusion. Method: We developed new models using multi-view variational autoencoder (MVAE) for feature representation learning and a product of expert (PoE) model for multi-view information fusion. We applied the proposed models to an in-house Louisiana Osteoporosis Study (LOS) cohort with 931 male subjects, including 345 African Americans and 586 Caucasians. With an analytical solution of the product of Gaussian distribution, we adopted variational inference to train the designed MVAE-PoE model to perform common latent feature extraction. We performed genome-wide association studies (GWAS) to select 256 genetic variants with the lowest p-values for each proximal femoral strength and integrated whole genome sequence (WGS) features and DXA-derived imaging features to predict proximal femoral strength. Results: The best prediction model for fall fracture load was acquired by integrating WGS features and DXA-derived imaging features. The designed models achieved the mean absolute percentage error of 18.04%, 6.84% and 7.95% for predicting proximal femoral fracture loads using linear models of fall loading, nonlinear models of fall loading, and nonlinear models of stance loading, respectively. Compared to existing multi-view information fusion methods, the proposed MVAE-PoE achieved the best performance. Conclusion: The proposed models are capable of predicting proximal femoral strength using WGS features and DXA-derived imaging features. Though this tool is not a substitute for FEA using QCT images, it would make improved assessment of hip fracture risk more widely available while avoiding the increased radiation dosage and clinical costs from QCT.

cs.LG↗
arXiv2023

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model

Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-required. They need to train a time-dependent classifier or a condition-dependent score estimator, which increases the cost of constructing conditional diffusion models and is inconvenient to transfer across different conditions. Some current works aim to overcome this limitation by proposing training-free solutions, but most can only be applied to a specific category of tasks and not to more general conditions. In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions. Specifically, we leverage off-the-shelf pre-trained networks, such as a face detection model, to construct time-independent energy functions, which guide the generation process without requiring training. Furthermore, because the construction of the energy function is very flexible and adaptable to various conditions, our proposed FreeDoM has a broader range of applications than existing training-free methods. FreeDoM is advantageous in its simplicity, effectiveness, and low cost. Experiments demonstrate that FreeDoM is effective for various conditions and suitable for diffusion models of diverse data domains, including image and latent code domains.

cs.CV↗
arXiv2023

Hyperbolicity of the base of an admissible family of log canonical stable minimal models

We investigate the stratified hyperbolicity properties of Birkar's moduli stack of log canonical (lc) stable minimal models. The main technical result is a construction of Viehweg-Zuo's system of Higgs sheaves associated with an admissible family of lc stable minimal models, using the theory of degenerations of Hodge structure and non-abelian Hodge theory.

math.AG↗
arXiv2023

Open Set Action Recognition via Multi-Label Evidential Learning

Existing methods for open-set action recognition focus on novelty detection that assumes video clips show a single action, which is unrealistic in the real world. We propose a new method for open set action recognition and novelty detection via MUlti-Label Evidential learning (MULE), that goes beyond previous novel action detection methods by addressing the more general problems of single or multiple actors in the same scene, with simultaneous action(s) by any actor. Our Beta Evidential Neural Network estimates multi-action uncertainty with Beta densities based on actor-context-object relation representations. An evidence debiasing constraint is added to the objective function for optimization to reduce the static bias of video representations, which can incorrectly correlate predictions and static cues. We develop a learning algorithm based on a primal-dual average scheme update to optimize the proposed problem. Theoretical analysis of the optimization algorithm demonstrates the convergence of the primal solution sequence and bounds for both the loss function and the debiasing constraint. Uncertainty and belief-based novelty estimation mechanisms are formulated to detect novel actions. Extensive experiments on two real-world video datasets show that our proposed approach achieves promising performance in single/multi-actor, single/multi-action settings.

cs.CV↗
arXiv2023

$L^2$-Dolbeault resolution of the lowest Hodge piece of a Hodge module

In this paper, we introduce a coherent subsheaf of Saito's $S$-sheaf, which is a combination of the $S$-sheaf and the multiplier ideal sheaf. We construct its $L^2$-Dolbeault resolution, which generalizes MacPherson's conjecture on the $L^2$ resolution of the Grauert-Riemenschneider sheaf. We also prove various vanishing theorems for the $S$-sheaf (Saito's vanishing theorem, Kawamata-Viehweg vanishing theorem and some new ones like Nadel vanishing theorem) transcendentally. Finally, we discuss some applications of our results on the relative version of Fujita's conjecture (e.g. Kawamata's conjecture).

math.AG↗