Search Results for author:
Found 221 papers, 109 papers with code
Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction
However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.
Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges
In addition, we introduce a biologically grounded evaluation metric that better reflects the inherent heterogeneity in single-cell responses.
AlphaFold Database Debiasing for Robust Inverse Folding
The AlphaFold Protein Structure Database (AFDB) offers unparalleled structural coverage at near-experimental accuracy, positioning it as a valuable resource for data-driven protein design.
PFMBench: Protein Foundation Model Benchmark
To fill this gap, we present PFMBench, a comprehensive benchmark evaluating protein foundation models across 38 tasks spanning 8 key areas of protein science.
Tokenizing Electron Cloud in Protein-Ligand Interaction Learning
The affinity and specificity of protein-molecule binding directly impact functional outcomes, uncovering the mechanisms underlying biological regulation and signal transduction.
GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype
We propose GRAPE, a heterogeneous graph neural network (HGNN) that leverages gene representations initialized with features from descriptions and sequences, models the distinct roles of genes with different biotypes, and dynamically refines the GRN through GSL.
Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks
Data-free Knowledge Distillation (DFKD) is a method that constructs pseudo-samples using a generator without real data, and transfers knowledge from a teacher model to a student by enforcing the student to overcome dimensional differences and learn to mimic the teacher's outputs on these pseudo-samples.
Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification
As for data flow, we propose a unified pipeline to integrate multi-omics data by reverse-transcribing RNA and reverse-translating amino acids into nucleotide-based sequences.
A Simple yet Effective DDG Predictor is An Unsupervised Antibody Optimizer and Explainer
For the target antibody, we propose a novel Mutation Explainer to learn mutation preferences, which accounts for the marginal benefit of each mutation per residue.
G2PDiffusion: Genotype-to-Phenotype Prediction with Diffusion Models
Discovering the genotype-phenotype relationship is crucial for genetic engineering, which will facilitate advances in fields such as crop breeding, conservation biology, and personalized medicine.
PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
Phylogenetic trees elucidate evolutionary relationships among species, but phylogenetic inference remains challenging due to the complexity of combining continuous (branch lengths) and discrete parameters (tree topology).
Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimization
Antibodies are Y-shaped proteins that protect the host by binding to specific antigens, and their binding is mainly determined by the Complementary Determining Regions (CDRs) in the antibody.
DapPep: Domain Adaptive Peptide-agnostic Learning for Universal T-cell Receptor-antigen Binding Affinity Prediction
Identifying T-cell receptors (TCRs) that interact with antigenic peptides provides the technical basis for developing vaccines and immunotherapies.
Pan-protein Design Learning Enables Task-adaptive Generalization for Low-resource Enzyme Design
Computational protein design (CPD) offers transformative potential for bioengineering, but current deep CPD models, focused on universal domains, struggle with function-specific designs.
Revisiting Marr in Face: The Building of 2D--2.5D--3D Representations in Deep Neural Networks
By injecting graphics probes into neural networks, and analyzing their behavior in reconstructing images, we find that DNNs initially encode images as 2D representations in low-level layers, and finally construct 3D representations in high-level layers.
FM-TS: Flow Matching for Time Series Generation
FM-TS is more efficient in terms of training and inference.
MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction
Post-translational modifications (PTMs) profoundly expand the complexity and functionality of the proteome, regulating protein attributes and interactions that are crucial for biological processes.
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
Molecular relational learning (MRL) is crucial for understanding the interaction behaviors between molecular pairs, a critical aspect of drug discovery and development.
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
This paper delves into the interplay between vision backbones and optimizers, unvealing an inter-dependent phenomenon termed \textit{\textbf{b}ackbone-\textbf{o}ptimizer \textbf{c}oupling \textbf{b}ias} (BOCB).
A Review of BioTree Construction in the Context of Information Fusion: Priors, Methods, Applications and Trends
By addressing the challenges of data complexity and prior knowledge integration, this review aims to inspire interdisciplinary innovation at the intersection of biology and DL.
Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
In this paper, we rethink the roles played by graph structural information in graph data training and identify that message passing is not the only path to modeling structural information.
A Survey on Mixup Augmentations and Beyond
As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable.
MetaEnzyme: Meta Pan-Enzyme Learning for Task-Adaptive Redesign
Enzyme design plays a crucial role in both industrial production and biology.
SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition
With the help of flexible prompting and gated alignments, SSPA is generalizable to specific domains.
Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation
To bridge the gaps between powerful Graph Neural Networks (GNNs) and lightweight Multi-Layer Perceptron (MLPs), GNN-to-MLP Knowledge Distillation (KD) proposes to distill knowledge from a well-trained teacher GNN into a student MLP.
The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges
In this survey, we provide a comprehensive review of the latest progress on heterophilic graph learning, including an extensive summary of benchmark datasets and evaluation of homophily metrics on synthetic graphs, meticulous classification of the most updated supervised and unsupervised learning methods, thorough digestion of the theoretical analysis on homophily/heterophily, and broad exploration of the heterophily-related applications.
BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical Science
On the widely used popular knowledge graph, we discover over 90 factual errors which provide scenarios for agents to make discoveries and demonstrate the effectiveness of our approach.
NovoBench: Benchmarking Deep Learning-based De Novo Peptide Sequencing Methods in Proteomics
In this work, we present the first unified benchmark NovoBench for \emph{de novo} peptide sequencing, which comprises diverse mass spectrum data, integrated models, and comprehensive evaluation metrics.
CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
To broaden the scope, we have adapted these models to a range of tasks essential in drug design, which are considered sub-tasks within the graph fill-in-the-blank tasks.
Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences
To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favorable practice of using non-data-dependent memory pattern, i. e., emphasize the near and neglect the distant, to processing sequences.
FoldToken2: Learning compact, invariant and generative protein structure language
The equivalent nature of 3D coordinates has posed long term challenges in protein structure representation learning, alignment, and generation.
Set-CLIP: Exploring Aligned Semantic From Low-Alignment Multimodal Data Through A Distribution View
Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances.
Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions
Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields and have shown significant potential in the academic peer-review process.
GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models
The Genomic Foundation Model (GFM) paradigm is expected to facilitate the extraction of generalizable representations from massive genomic data, thereby enabling their application across a spectrum of downstream applications.
Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bases.
UniIF: Unified Molecule Inverse Folding
We do such unification in two levels: 1) Data-Level: We propose a unified block graph data form for all molecules, including the local frame building and geometric feature initialization.
Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning
Protein-protein bindings play a key role in a variety of fundamental biological processes, and thus predicting the effects of amino acid mutations on protein-protein binding is crucial.
VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling
In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning.
LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences.
AdaNovo: Adaptive \emph{De Novo} Peptide Sequencing with Conditional Mutual Information
Moreover, AdaNovo excels in identifying amino acids with PTMs and exhibits robustness against data noise.
Advances of Deep Learning in Protein Science: A Comprehensive Survey
Protein representation learning plays a crucial role in understanding the structure and function of proteins, which are essential biomolecules involved in various biological processes.
A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation
As a result, TGS enjoys the benefits of graph topology awareness in training but is free from data dependency in inference.
PPFlow: Target-aware Peptide Design with Torsional Flow Matching
Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades.
Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
In this paper, we identify two important collaborative processes for this topic: (1) select: how to select an optimal task combination from a given task pool based on their compatibility, and (2) weigh: how to weigh the selected tasks based on their importance.
Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions
Augmentation is an effective alternative to utilize the small amount of labeled protein data.
FGBERT: Function-Driven Pre-trained Gene Language Model for Metagenomics
Metagenomic data, comprising mixed multi-species genomes, are prevalent in diverse environments like oceans and soils, significantly impacting human health and ecological functions.
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding
In addition, microenvironments defined in previous work are largely based on experimentally assayed physicochemical properties, for which the "vocabulary" is usually extremely small.
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Exponential Moving Average (EMA) is a widely used weight averaging (WA) regularization to learn flat optima for better generalizations without extra cost in deep neural network (DNN) optimization.
PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction
Compound-Protein Interaction (CPI) prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery.
A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
(4) The edge-centric pretraining framework GraphsGPT demonstrates its efficacy in graph domain tasks, excelling in both representation and generation.
FoldToken: Learning Protein Language via Vector Quantization and Beyond
Is there a foreign language describing protein sequences and structures simultaneously?
MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning.
Must: Maximizing Latent Capacity of Spatial Transcriptomics Data
MuST integrates the multi-modality information contained in the ST data effectively into a uniform latent space to provide a foundation for all the downstream tasks.
Deep Manifold Transformation for Protein Representation Learning
Protein representation learning is critical in various tasks in biology, such as drug design and protein structure or function prediction, which has primarily benefited from protein language models and graph neural networks.
Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding
Representing graph data in a low-dimensional space for subsequent tasks is the purpose of attributed graph embedding.
Graph-level Protein Representation Learning by Structure Knowledge Refinement
The mainstream method is utilizing contrastive learning to facilitate graph feature extraction, known as Graph Contrastive Learning (GCL).
General Point Model Pretraining with Autoencoding and Autoregressive
Compared to models like Point-BERT MaskPoint and PointMAE our GPM achieves superior performance in point cloud understanding tasks.
Masked Modeling for Self-supervised Representation Learning on Vision and Beyond
As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data.
Progressive Multi-Modality Learning for Inverse Protein Folding
While deep generative models show promise for learning inverse protein folding directly from data, the lack of publicly available structure-sequence pairings limits their generalization.
Efficiently Predicting Protein Stability Changes Upon Single-point Mutation with Large Language Models
Predicting protein stability changes induced by single-point mutations has been a persistent challenge over the years, attracting immense interest from numerous researchers.
Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
Remarkably, we show that even smaller base models, when equipped with our proposed approach, can achieve results comparable to those of larger models, illustrating the potential of our approach in harnessing the power of rationales for improved multimodal reasoning.
Ranked #1 on
Science Question Answering
on ScienceQA
Segment Anything in Defect Detection
Defect detection plays a crucial role in infrared non-destructive testing systems, offering non-contact, safe, and efficient inspection capabilities.
General Point Model with Autoencoding and Autoregressive
This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks.
USTEP: Spatio-Temporal Predictive Learning under A Unified View
In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective.
SemiReward: A General Reward Model for Semi-supervised Learning
The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.
Co-modeling the Sequential and Graphical Routes for Peptide Representation Learning
Peptides are formed by the dehydration condensation of multiple amino acids.
CONVERT:Contrastive Graph Clustering with Reliable Augmentation
To address these problems, we propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (CONVERT).
Reinforcement Graph Clustering with Unknown Cluster Number
To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC).
Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework
Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks.
Efficient Prediction of Peptide Self-assembly through Sequential and Graphical Encoding
In recent years, there has been an explosion of research on the application of deep learning to the prediction of various peptide properties, due to the significant development and market potential of peptides.
Why Deep Models Often cannot Beat Non-deep Counterparts on Molecular Property Prediction?
Molecular property prediction (MPP) is a crucial task in the drug discovery pipeline, which has recently gained considerable attention thanks to advances in deep neural networks.
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner.
Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs
To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP.
Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
In this way, however, it is hard to generate realistic fragments with complicated structures.
Dink-Net: Neural Clustering on Large Graphs
Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner.
Knowledge-Design: Pushing the Limit of Protein Design via Knowledge Refinement
After witnessing the great success of pretrained models on diverse protein-related tasks and the fact that recovery is highly correlated with confidence, we wonder whether this knowledge can push the limits of protein design further.
Ranked #1 on
Word Sense Disambiguation
on TS50
MotifRetro: Exploring the Combinability-Consistency Trade-offs in retrosynthesis via Dynamic Motif Editing
Is there a unified framework for graph-based retrosynthesis prediction?
Extracting Low-/High- Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework
Furthermore, we identified a potential information drowning problem for existing GNN-to-MLP distillation, i. e., the high-frequency knowledge of the pre-trained GNNs may be overwhelmed by the low-frequency knowledge during distillation; we have described in detail what it represents, how it arises, what impact it has, and how to deal with it.
Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module
Additionally, we reveal the drawbacks of previous residual methods, such as the lack of node adaptability and severe loss of high-order neighborhood subgraph information, and propose a \textbf{Posterior-Sampling-based, Node-Adaptive Residual module (PSNR)}.
FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing
The availability of handy multi-modal (i. e., RGB-D) sensors has brought about a surge of face anti-spoofing research.
High-dimensional Clustering onto Hamiltonian Cycle
Then, the anchors of different clusters are sorted on the optimal Hamiltonian cycle generated by the cluster similarities and mapped on the circumference of a circle.
Cross-Gate MLP with Protein Complex Invariant Embedding is A One-Shot Antibody Designer
In this paper, we propose a \textit{simple yet effective} model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner.
InstructBio: A Large-scale Semi-supervised Learning Paradigm for Biochemical Problems
In the field of artificial intelligence for science, it is consistently an essential challenge to face a limited amount of labeled data for real-world problems.
Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias
It has become cognitive inertia to employ cross-entropy loss function in classification related tasks.
CCPL: Cross-modal Contrastive Protein Learning
Effective protein representation learning is crucial for predicting protein functions.
CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment
In this work, we propose a novel contrastive visual-textual transformation for SLR, CVT-SLR, to fully explore the pretrained knowledge of both the visual and language modalities.
PrefixMol: Target- and Chemistry-aware Molecule Design via Prefix Embedding
Is there a unified model for generating molecules considering different conditions, such as binding pockets and chemical properties?
Improving (Dis)agreement Detection with Inductive Social Relation Information From Comment-Reply Interactions
(Dis)agreement detection aims to identify the authors' attitudes or positions (\textit{{agree, disagree, neutral}}) towards a specific text.
Characterization and Generation of 3D Realistic Geological Particles with Metaball Descriptor based on X-Ray Computed Tomography
This algorithm can capture the main contour of parental particles with a series of non-overlapping spheres and refine surface-texture details through gradient search.
Data-Efficient Protein 3D Geometric Pretraining via Refinement of Diffused Protein Structure Decoy
Learning meaningful protein representation is important for a variety of biological downstream tasks such as structure-based drug design.
RDesign: Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
We crafted a large, well-curated benchmark dataset and designed a comprehensive structural modeling approach to represent the complex RNA tertiary structure.
DiffSDS: A language diffusion model for protein backbone inpainting under geometric conditions and constraints
Have you ever been troubled by the complexity and computational cost of SE(3) protein structure modeling and been amazed by the simplicity and power of language modeling?
Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching
It takes advantage of MatchExplainer to fix the most informative portion of the graph and merely operates graph augmentations on the rest less informative part.
Surveillance Face Anti-spoofing
In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks.
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
Ranked #3 on
Universal Domain Adaptation
on Office-31
A Survey on Protein Representation Learning: Retrospect and Prospect
To pave the way for AI researchers with little bioinformatics background, we present a timely and comprehensive review of PRL formulations and existing PRL methods from the perspective of model architectures, pretext tasks, and downstream applications.
Federated Learning for Inference at Anytime and Anywhere
Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, and support for diverse device capabilities.
Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networks
Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area.
Deciphering RNA Secondary Structure Prediction: A Probabilistic K-Rook Matching Perspective
In this work, we reformulate the RNA secondary structure prediction as a K-Rook problem, thereby simplifying the prediction process into probabilistic matching within a finite solution space.
Protein Language Models and Structure Prediction: Connection and Progression
The prediction of protein structures from sequences is an important task for function prediction, drug design, and related biological processes understanding.
A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource
However, the corresponding survey paper is relatively scarce, and it is imminent to make a summary of this field.
SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning
Recent years have witnessed remarkable advances in spatiotemporal predictive learning, with methods incorporating auxiliary inputs, complex neural architectures, and sophisticated training strategies.
Ranked #2 on
Video Prediction
on Moving MNIST
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier
The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks.
DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
Previous works usually generate atoms in an auto-regressive way, where element types and 3D coordinates of atoms are generated one by one.
EVNet: An Explainable Deep Network for Dimension Reduction
The proposed techniques are integrated with a visual interface to help the user to adjust EVNet to achieve better DR performance and explainability.
MogaNet: Multi-order Gated Aggregation Network
Notably, MogaNet hits 80. 0\% and 87. 8\% accuracy with 5. 2M and 181M parameters on ImageNet-1K, outperforming ParC-Net and ConvNeXt-L, while saving 59\% FLOPs and 17M parameters, respectively.
Ranked #1 on
Instance Segmentation
on COCO val2017
Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation
Therefore, we propose to introduce additional word-level semantic knowledge of sign language linguistics to assist in improving current end-to-end neural SLT models.
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings
Although contextualized embeddings generated from large-scale pre-trained models perform well in many tasks, traditional static embeddings (e. g., Skip-gram, Word2Vec) still play an important role in low-resource and lightweight settings due to their low computational cost, ease of deployment, and stability.
Ranked #1 on
Word Similarity
on WS353
A Systematic Survey of Chemical Pre-trained Models
Deep learning has achieved remarkable success in learning representations for molecules, which is crucial for various biochemical applications, ranging from property prediction to drug design.
Automated Graph Self-supervised Learning via Multi-teacher Knowledge Distillation
Self-supervised learning on graphs has recently achieved remarkable success in graph representation learning.
Teaching Yourself: Graph Self-Distillation on Neighborhood for Node Classification
Despite their great academic success, Multi-Layer Perceptrons (MLPs) remain the primary workhorse for practical industrial applications.
PiFold: Toward effective and efficient protein inverse folding
How can we design protein sequences folding into the desired structures effectively and efficiently?
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs).
A Survey on Generative Diffusion Model
Deep generative models are a prominent approach for data generation, and have been used to produce high quality samples in various domains.
What Does the Gradient Tell When Attacking the Graph Structure
To address this issue, we propose a novel surrogate model with multi-level propagation that preserves the node dissimilarity information.
Are Gradients on Graph Structure Reliable in Gray-box Attacks?
These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the meta-gradient on the graph structure.
Exploring Generative Neural Temporal Point Process
While lots of previous works have focused on `goodness-of-fit' of TPP models by maximizing the likelihood, their predictive performance is unsatisfactory, which means the timestamps generated by models are far apart from true observations.
UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection
We propose that the ideal DR approach combines both FS and FP into a unified end-to-end manifold learning framework, simultaneously performing fundamental feature discovery while maintaining the intrinsic relationships between data samples in the latent space.
Ranked #1 on
Dimensionality Reduction
on MCA
DLME: Deep Local-flatness Manifold Embedding
To overcome the underconstrained embedding problem, we design a loss and theoretically demonstrate that it leads to a more suitable embedding based on the local flatness.
Ranked #2 on
Image Classification
on ImageNet-100 (TEMI Split)
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
Spatiotemporal predictive learning aims to generate future frames by learning from historical frames.
Ranked #14 on
Video Prediction
on Moving MNIST
CoSP: Co-supervised pretraining of pocket and ligand
Can we inject the pocket-ligand interaction knowledge into the pre-trained model and jointly learn their chemical space?
SimVP: Simpler yet Better Video Prediction
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies.
Ranked #4 on
Video Prediction
on Human3.6M
Hyperspherical Consistency Regularization
Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier.
Discovering and Explaining the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions
Graph neural networks (GNNs) mainly rely on the message-passing paradigm to propagate node features and build interactions, and different graph learning tasks require different ranges of node interactions.
MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames
In this paper, we consider a novel problem of reconstructing a 3D human avatar from multiple unconstrained frames, independent of assumptions on camera calibration, capture space, and constrained actions.
Generative De Novo Protein Design with Global Context
Thus, we propose the Global-Context Aware generative de novo protein design method (GCA), consisting of local and global modules.
DiffMD: A Geometric Diffusion Model for Molecular Dynamics Simulations
To waive this requirement, we propose a novel model called DiffMD by directly estimating the gradient of the log density of molecular conformations.
STONet: A Neural-Operator-Driven Spatio-temporal Network
Graph-based spatio-temporal neural networks are effective to model the spatial dependency among discrete points sampled irregularly from unstructured grids, thanks to the great expressiveness of graph neural networks.
Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape
3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.
Harnessing Hard Mixed Samples with Decoupled Regularizer
However, we found that the extra optimizing step may be redundant because label-mismatched mixed samples are informative hard mixed samples for deep models to localize discriminative features.
A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications
Pretrained Language Models (PLMs) such as BERT have revolutionized the landscape of Natural Language Processing (NLP).
Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transport
Training data are usually limited or heterogeneous in many chemical and biological applications.
SemiRetro: Semi-template framework boosts deep retrosynthesis prediction
Experimental results show that SemiRetro significantly outperforms both existing TB and TF methods.
Ranked #5 on
Single-step retrosynthesis
on USPTO-50k
Target-aware Molecular Graph Generation
Building on the recent advantages of flow-based molecular generation models, we propose SiamFlow, which forces the flow to fit the distribution of target sequence embeddings in latent space.
SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
Furthermore, we devise adversarial training scheme, dubbed \textbf{AT-SimGRACE}, to enhance the robustness of graph contrastive learning and theoretically explain the reasons.
AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB
While DeepMind has tentatively solved protein folding, its inverse problem -- protein design which predicts protein sequences from their 3D structures -- still faces significant challenges.
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Accordingly, we propose $\eta$-balanced mixup loss for complementary learning of the two sub-objectives.
Ranked #7 on
Image Classification
on Places205
GenURL: A General Framework for Unsupervised Representation Learning
For example, dimension reduction methods, t-SNE, and UMAP optimize pair-wise data relationships by preserving the global geometric structure, while self-supervised learning, SimCLR, and BYOL focus on mining the local statistics of instances under specific augmentations.
Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks
Gray-box graph attacks aim at disrupting the performance of the victim model by using inconspicuous attacks with limited knowledge of the victim model.
ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
Contrastive Learning (CL) has emerged as a dominant technique for unsupervised representation learning which embeds augmented versions of the anchor close to each other (positive samples) and pushes the embeddings of other samples (negatives) apart.
Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs
Then HMGs are constructed with both atom-level and motif-level nodes.
Beyond Message Passing Paradigm: Training Graph Data with Consistency Constraints
Specifically, the GCL framework is optimized with three well-designed consistency constraints: neighborhood consistency, label consistency, and class-center consistency.
Improving Discriminative Visual Representation Learning via Automatic Mixup
In this paper, we decompose mixup into two sub-tasks of mixup generation and classification and formulate it for discriminative representations as class- and instance-level mixup.
Co-learning: Learning from Noisy Labels with Self-supervision
Noisy labels, resulting from mistakes in manual labeling or webly data collecting for supervised learning, can cause neural networks to overfit the misleading information and degrade the generalization performance.
A Data-driven feature selection and machine-learning model benchmark for the prediction of longitudinal dispersion coefficient
Then, a global optimal feature set (the channel width, the flow velocity, the channel slope and the cross sectional area) was proposed through numerical comparison of the distilled local optimums in performance with representative ML models.
Exploring Localization for Self-supervised Fine-grained Contrastive Learning
Self-supervised contrastive learning has demonstrated great potential in learning visual representations.
Ranked #29 on
Fine-Grained Image Classification
on CUB-200-2011
A data-based comparative review and AI-driven symbolic model for longitudinal dispersion coefficient in natural streams
Whereas implicit ML-driven methods are black-boxes in nature, explicit ML-driven methods have more potential in prediction of LDC.
Unsupervised Deep Manifold Attributed Graph Embedding
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.
Ranked #2 on
Node Clustering
on Pubmed
Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection
To bridge the gap to real-world applications, we introduce a largescale High-Fidelity Mask dataset, namely CASIA-SURF HiFiMask (briefly HiFiMask).
InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?
Sentence insertion is an interesting NLP problem but received insufficient attention.
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #8 on
Image Classification
on Places205
Towards Robust Graph Neural Networks against Label Noise
A pseudo label is computed from the neighboring labels for each node in the training set using LP; meta learning is utilized to learn a proper aggregation of the original and pseudo label as the final label.
Deep Manifold Computing and Visualization Using Elastic Locally Isometric Smoothness
The ability to preserve local geometry of highly nonlinear manifolds in high dimensional spaces and properly unfold them into lower dimensional hyperplanes is the key to the success of manifold computing, nonlinear dimensionality reduction (NLDR) and visualization.
Consistent Representation Learning for High Dimensional Data Analysis
In this paper, we propose a novel neural network-based method, called Consistent Representation Learning (CRL), to accomplish the three associated tasks end-to-end and improve the consistencies.
Face Forgery Detection by 3D Decomposition
Detecting digital face manipulation has attracted extensive attention due to fake media's potential harms to the public.
NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
Face anti-spoofing (FAS) plays a vital role in securing face recognition systems.
Deep Manifold Transformation for Nonlinear Dimensionality Reduction
The LGP constraints constitute the loss for deep manifold learning and serve as geometric regularizers for NLDR network training.
Invertible Manifold Learning for Dimension Reduction
Dimension reduction (DR) aims to learn low-dimensional representations of high-dimensional data with the preservation of essential information.
Deep Clustering and Representation Learning that Preserves Geometric Structures
To overcome the problem that clusteringoriented losses may deteriorate the geometric structure of embeddings in the latent space, an isometric loss is proposed for preserving intra-manifold structure locally and a ranking loss for inter-manifold structure globally.
Clustering Based on Graph of Density Topology
GDT jointly considers the local and global structures of data samples: firstly forming local clusters based on a density growing process with a strategy for properly noise handling as well as cluster boundary detection; and then estimating a GDT from relationship between local clusters in terms of a connectivity measure, givingglobal topological graph.
Generalized Clustering and Multi-Manifold Learning with Geometric Structure Preservation
Though manifold-based clustering has become a popular research topic, we observe that one important factor has been omitted by these works, namely that the defined clustering loss may corrupt the local and global structure of the latent space.
Towards Fast, Accurate and Stable 3D Dense Face Alignment
Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously.
Ranked #1 on
3D Face Reconstruction
on Florence
(Mean NME metric)
Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
Gesture recognition has attracted considerable attention owing to its great potential in applications.
SADet: Learning An Efficient and Accurate Pedestrian Detector
Although the anchor-based detectors have taken a big step forward in pedestrian detection, the overall performance of algorithm still needs further improvement for practical applications, \emph{e. g.}, a good trade-off between the accuracy and efficiency.
Markov-Lipschitz Deep Learning
We propose a novel framework, called Markov-Lipschitz deep learning (MLDL), to tackle geometric deterioration caused by collapse, twisting, or crossing in vector-based neural network transformations for manifold-based representation learning and manifold data generation.
Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review
Although ethnic bias has been verified to severely affect the performance of face recognition systems, it still remains an open research problem in face anti-spoofing.
Learning Meta Face Recognition in Unseen Domains
Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization.
CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing
Ethnic bias has proven to negatively affect the performance of face recognition systems, and it remains an open research problem in face anti-spoofing.
Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing
Regardless of the usage of deep learning and handcrafted methods, the dynamic information from videos and the effect of cross-ethnicity are rarely considered in face anti-spoofing.
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them.
Ranked #37 on
Object Detection
on COCO-O
WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild.
Ranked #3 on
Object Detection
on WiderPerson
(mMR metric)
Relational Learning for Joint Head and Human Detection
Head and human detection have been rapidly improved with the development of deep convolutional neural networks.
PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Pedestrian detection in crowded scenes is a challenging problem, because occlusion happens frequently among different pedestrians.
RefineFace: Refinement Neural Network for High Performance Face Detection
To improve the classification ability for high recall efficiency, STC first filters out most simple negatives from low level detection layers to reduce search space for subsequent classifier, then SML is applied to better distinguish faces from background at various scales and FSM is introduced to let the backbone learn more discriminative features for classification.
CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and modalities.
ChaLearn Looking at People: IsoGD and ConGD Large-scale RGB-D Gesture Recognition
The ChaLearn large-scale gesture recognition challenge has been run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than $200$ teams round the world.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Improved Selective Refinement Network for Face Detection
With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years.
Improving Face Anti-Spoofing by 3D Virtual Synthesis
Specifically, we consider a printed photo as a flat surface and mesh it into a 3D object, which is then randomly bent and rotated in 3D space.
Ranked #1 on
Face Anti-Spoofing
on CASIA-MFSD
A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing
To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and visual modalities.
Selective Refinement Network for High Performance Face Detection
In particular, the SRN consists of two modules: the Selective Two-step Classification (STC) module and the Selective Two-step Regression (STR) module.
Ranked #1 on
Face Detection
on PASCAL Face
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other.
Ranked #10 on
Pedestrian Detection
on Caltech
(using extra training data)
Large-scale Bisample Learning on ID Versus Spot Face Recognition
In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition.
Face Synthesis for Eyeglass-Robust Face Recognition
A feasible method is to collect large-scale face images with eyeglasses for training deep learning methods.
Ensemble Soft-Margin Softmax Loss for Image Classification
On the other hand, the learned classifier of softmax loss is weak.
Face Alignment in Full Pose Range: A 3D Total Solution
In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks.
Ranked #3 on
Face Alignment
on AFLW
Single-Shot Refinement Neural Network for Object Detection
For object detection, the two-stage approach (e. g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e. g., SSD) has the advantage of high efficiency.
Ranked #180 on
Object Detection
on COCO test-dev
S3FD: Single Shot Scale-Invariant Face Detector
This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S3FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces.
FaceBoxes: A CPU Real-time Face Detector with High Accuracy
The MSCL aims at enriching the receptive fields and discretizing anchors over different layers to handle faces of various scales.
Ranked #3 on
Face Detection
on PASCAL Face
S$^3$FD: Single Shot Scale-invariant Face Detector
This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S$^3$FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces.
Ranked #2 on
Face Detection
on PASCAL Face
Learning Efficient Image Representation for Person Re-Identification
Then, a robust image representation based on color names is obtained by concatenating the statistical descriptors in each stripe.
Exclusivity-Consistency Regularized Multi-View Subspace Clustering
Multi-view subspace clustering aims to partition a set of multi-source data into their underlying groups.
Deep Person Re-Identification with Improved Embedding and Efficient Training
However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows.
Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition
Recently, the popularity of depth-sensors such as Kinect has made depth videos easily available while its advantages have not been fully exploited.
Embedding Deep Metric for Person Re-identication A Study Against Large Variations
From this point of view, selecting suitable positive i. e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations.
Learning Discriminative Features with Class Encoder
Deep neural networks usually benefit from unsupervised pre-training, e. g. auto-encoders.
CRAFT Objects from Images
They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories.
Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification
We argue that the PSD constraint provides a useful regularization to smooth the solution of the metric, and hence the learned metric is more robust than without the PSD constraint.
Adaptively Unified Semi-Supervised Dictionary Learning With Active Points
In this paper, we present a novel semi-supervised dictionary learning method, which uses the informative coding vectors of both labeled and unlabeled data, and adaptively emphasizes the high confidence coding vectors of unlabeled data to enhance the dictionary discriminative capability simultaneously.
