Search Results for author:
Found 50 papers, 31 papers with code
Lightweight Contrastive Protein Structure-Sequence Transformation
In this work, we introduce a novel unsupervised protein structure representation pretraining with a robust protein language model.
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.
Explaining Graph Neural Networks via Non-parametric Subgraph Matching
The great success in graph neural networks (GNNs) provokes the question about explainability: Which fraction of the input graph is the most determinant of the prediction?
Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery
We show that such lossless primitives can drastically improve the performance of hierarchical policies.
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels
The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions.
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.
Efficient Multi-order Gated Aggregation Network
Since the recent success of Vision Transformers (ViTs), explorations toward ViT-style architectures have triggered the resurgence of ConvNets.
Ranked #1 on
Instance Segmentation
on COCO test-dev
(AP50 metric)
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.
Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning
In this work, we develop a novel identity detection reinforcement learning (IDRL) framework that allows an agent to dynamically infer the identities of nearby agents and select an appropriate policy to accomplish the task.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
CUP: Critic-Guided Policy Reuse
The ability to reuse previous policies is an important aspect of human intelligence.
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
With the remarkable progress of deep neural networks in computer vision, data mixing augmentation techniques are widely studied to alleviate problems of degraded generalization when the amount of training data is limited.
MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization
We evaluate the proposed approach on three real-world index datasets and compare it to state-of-the-art baselines.
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.
Tracking Every Thing in the Wild
Our experiments show that TETA evaluates trackers more comprehensively, and TETer achieves significant improvements on the challenging large-scale datasets BDD100K and TAO compared to the state-of-the-art.
Ranked #6 on
Multiple Object Tracking
on BDD100K val
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 #1 on
Image Classification
on ImageNet-100
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
Spatiotemporal predictive learning aims to generate future frames by learning from historical frames.
Ranked #11 on
Video Prediction
on Moving MNIST
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.
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
Based on this fact, we propose an Architecture-Agnostic Masked Image Modeling framework (A$^2$MIM), which is compatible with both Transformers and CNNs in a unified way.
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.
A heuristic method for data allocation and task scheduling on heterogeneous multiprocessor systems under memory constraints
Computing workflows in heterogeneous multiprocessor systems are frequently modeled as directed acyclic graphs of tasks and data blocks, which represent computational modules and their dependencies in the form of data produced by a task and used by others.
neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning
Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.
UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era.
Ranked #1 on
Highlight Detection
on YouTube Highlights
Decoupled Mixup for Data-efficient Learning
This also leads to an interesting objective design problem for mixup training that we need to focus on both smoothing the decision boundaries and identifying discriminative features.
Style Transformer for Image Inversion and Editing
Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously.
A Shared Representation for Photorealistic Driving Simulators
We build on successful cGAN models to propose a new semantically-aware discriminator that better guides the generator.
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Mixup is a popular data-dependent augmentation technique for deep neural networks, which contains two sub-tasks, mixup generation, and classification.
Ranked #7 on
Image Classification
on Places205
GenURL: A General Framework for Unsupervised Representation Learning
Unsupervised representation learning (URL) that learns compact embeddings of high-dimensional data without supervision has achieved remarkable progress recently.
Offline Reinforcement Learning with Reverse Model-based Imagination
These reverse imaginations provide informed data augmentation for model-free policy learning and enable conservative generalization beyond the offline dataset.
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.
Exploring Localization for Self-supervised Fine-grained Contrastive Learning
Self-supervised contrastive learning has demonstrated great potential in learning visual representations.
Ranked #18 on
Fine-Grained Image Classification
on NABirds
Active Hierarchical Exploration with Stable Subgoal Representation Learning
Although GCHRL possesses superior exploration ability by decomposing tasks via subgoals, existing GCHRL methods struggle in temporally extended tasks with sparse external rewards, since the high-level policy learning relies on external rewards.
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 Wiki
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
Learning Subgoal Representations with Slow Dynamics
In goal-conditioned Hierarchical Reinforcement Learning (HRL), a high-level policy periodically sets subgoals for a low-level policy, and the low-level policy is trained to reach those subgoals.
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.
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.
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.
TLPG-Tracker: Joint Learning of Target Localization and Proposal Generation for Visual Tracking.
Target localization and proposal generation are two essential subtasks in generic visual tracking, and it is a challenge to address both the two efficiently.
Deformation-aware Unpaired Image Translation for Pose Estimation on Laboratory Animals
We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models.
Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
In addition, we also theoretically prove that optimizing low-level skills with this auxiliary reward will increase the task return for the joint policy.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Single Image Deraining: A Comprehensive Benchmark Analysis
We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images. This dataset highlights diverse data sources and image contents, and is divided into three subsets (rain streak, rain drop, rain and mist), each serving different training or evaluation purposes.
PFLD: A Practical Facial Landmark Detector
Being accurate, efficient, and compact is essential to a facial landmark detector for practical use.
Context-Aware Policy Reuse
Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks.
Fast Single Image Rain Removal via a Deep Decomposition-Composition Network
Rain effect in images typically is annoying for many multimedia and computer vision tasks.
Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs
We then construct three individual networks: a Focus-Net to extract depth from a single focal stack, a EDoF-Net to obtain the extended depth of field (EDoF) image from the focal stack, and a Stereo-Net to conduct stereo matching.
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database.
An Optimal Online Method of Selecting Source Policies for Reinforcement Learning
In this paper, we develop an optimal online method to select source policies for reinforcement learning.
A Learning-based Framework for Hybrid Depth-from-Defocus and Stereo Matching
Depth from defocus (DfD) and stereo matching are two most studied passive depth sensing schemes.
