Search Results for author:
Found 72 papers, 26 papers with code
Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples.
Ranked #22 on
Fine-Grained Image Classification
on CUB-200-2011
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture.
Ranked #20 on
Neural Architecture Search
on CIFAR-10
From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
By simply equipping it with an MLP layer for alignment, DINO surpasses CLIP in fine-grained related perception tasks.
Dual adaptive training of photonic neural networks
Photonic neural network (PNN) is a remarkable analog artificial intelligence (AI) accelerator that computes with photons instead of electrons to feature low latency, high energy efficiency, and high parallelism.
Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
In this paper, we propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) that leverages dynamical directed spatial dependencies and long-range temporal dependencies to improve the accuracy of long-term traffic forecasting.
Masked Autoencoders are Robust Data Augmentors
Specifically, MRA consistently enhances the performance on supervised, semi-supervised as well as few-shot classification.
SdAE: Self-distillated Masked Autoencoder
We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck.
Batch Normalization with Enhanced Linear Transformation
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions.
Trained Rank Pruning for Efficient Deep Neural Networks
We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training.
Trained Rank Pruning for Efficient Deep Neural Networks
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations.
TRP: Trained Rank Pruning for Efficient Deep Neural Networks
The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss, thus eliminating the fine-tuning process after low rank decomposition.
Motion-aware Contrastive Video Representation Learning via Foreground-background Merging
To alleviate such bias, we propose \textbf{F}oreground-b\textbf{a}ckground \textbf{Me}rging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others.
Bag of Instances Aggregation Boosts Self-supervised Distillation
Here bag of instances indicates a set of similar samples constructed by the teacher and are grouped within a bag, and the goal of distillation is to aggregate compact representations over the student with respect to instances in a bag.
Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation
In this paper, we propose a simple yet effective approach for self-supervised video object segmentation (VOS).
Deep Neural Network Compression with Single and Multiple Level Quantization
In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary). We are the first to consider the network quantization from both width and depth level.
MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization
We leverage the neural tangent kernel (NTK) theory to prove that our weight mean operation whitens activations and transits network into the chaotic regime like BN layer, and consequently, leads to an enhanced convergence.
Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation
Based on the STA score, we are able to progressively prune the tokens without introducing any additional parameters or requiring further re-training.
Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networks
This framework is general to endow arbitrary DNNs for solving linear inverse problems with convergence guarantees.
CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation
We introduce a novel method, CPPF++, designed for sim-to-real pose estimation.
Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
In this paper, we propose the first unified interpretation for existing zero-shot methods from the perspective of approximating the conditional posterior mean for the reverse diffusion process of conditional sampling.
Frequency-Aware Transformer for Learned Image Compression
Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years.
AiluRus: A Scalable ViT Framework for Dense Prediction
Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence.
Hierarchical Graph Networks for 3D Human Pose Estimation
Recent 2D-to-3D human pose estimation works tend to utilize the graph structure formed by the topology of the human skeleton.
Ranked #42 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
Light Field Reconstruction via Deep Adaptive Fusion of Hybrid Lenses
Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy.
Adapting Shortcut With Normalizing Flow: An Efficient Tuning Framework for Visual Recognition
To mitigate the computational and storage demands, recent research has explored Parameter-Efficient Fine-Tuning (PEFT), which focuses on tuning a minimal number of parameters for efficient adaptation.
Latency-Aware Differentiable Neural Architecture Search
However, these methods suffer the difficulty in optimizing network, so that the searched network is often unfriendly to hardware.
Zigzag Learning for Weakly Supervised Object Detection
Unlike them, we propose a zigzag learning strategy to simultaneously discover reliable object instances and prevent the model from overfitting initial seeds.
Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
In this paper, we propose a novel deep-based framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams.
Ensemble of Part Detectors for Simultaneous Classification and Localization
Part-based representation has been proven to be effective for a variety of visual applications.
DNQ: Dynamic Network Quantization
Network quantization is an effective method for the deployment of neural networks on memory and energy constrained mobile devices.
Picking Deep Filter Responses for Fine-Grained Image Recognition
Recognizing fine-grained sub-categories such as birds and dogs is extremely challenging due to the highly localized and subtle differences in some specific parts.
Group Re-Identification with Multi-grained Matching and Integration
The task of re-identifying groups of people underdifferent camera views is an important yet less-studied problem. Group re-identification (Re-ID) is a very challenging task sinceit is not only adversely affected by common issues in traditionalsingle object Re-ID problems such as viewpoint and human posevariations, but it also suffers from changes in group layout andgroup membership.
iPool -- Information-based Pooling in Hierarchical Graph Neural Networks
In this paper, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs.
AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groups
For this reason, we should use the geodesic to characterize how an image transform along the manifold of a transformation group, and adopt its length to measure the deviation between transformations.
FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
To this end, we present a novel regularization mechanism by learning the change of feature representations induced by a distribution of transformations without using the labels of data examples.
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events.
Graph Pooling with Node Proximity for Hierarchical Representation Learning
In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology.
Distilling Object Detectors with Task Adaptive Regularization
Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.
K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances.
Monotonic Robust Policy Optimization with Model Discrepancy
To mitigate the model discrepancy between training and target (testing) environments, domain randomization (DR) can generate plenty of environments with a sufficient diversity by randomly sampling environment parameters in simulator.
PAC-Bayesian Randomized Value Function with Informative Prior
To address this, in this paper, we propose a Bayesian linear regression with informative prior (IP-BLR) operator to leverage the data-dependent prior in the learning process of randomized value function, which can leverage the statistics of training results from previous iterations.
VEM-GCN: Topology Optimization with Variational EM for Graph Convolutional Networks
In the variational E-step, graph topology is optimized by approximating the posterior probability distribution of the latent adjacency matrix with a neural network learned from node embeddings.
Center-wise Local Image Mixture For Contrastive Representation Learning
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples.
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
In this paper, we propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to \textbf{Cross-samples and Multi-level} representation, and models the invariance to semantically similar images in a hierarchical way.
NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification
Therefore, it can relieve the over-smoothing issue and learn effective node representations over graphs with homophily or heterophily.
Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets regardless of their taxonomy labels, and followed by fine-tuning the pretrained model over specific dataset as usual.
Message Passing in Graph Convolution Networks via Adaptive Filter Banks
Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank.
Graph Neural Networks With Lifting-based Adaptive Graph Wavelets
To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information.
Learning Latent Architectural Distribution in Differentiable Neural Architecture Search via Variational Information Maximization
Existing differentiable neural architecture search approaches simply assume the architectural distribution on each edge is independent of each other, which conflicts with the intrinsic properties of architecture.
Variance Reduced Domain Randomization for Policy Gradient
In this paper, we theoretically derive a bias-free and state/environment-dependent optimal baseline for DR, and analytically show its ability to achieve further variance reduction over the standard constant and state-dependent baselines for DR. We further propose a variance reduced domain randomization (VRDR) approach for policy gradient methods, to strike a tradeoff between the variance reduction and computational complexity in practice.
Understanding Self-supervised Learning via Information Bottleneck Principle
To address this issue, we introduce the information bottleneck principle and propose the Self-supervised Variational Information Bottleneck (SVIB) learning framework.
Graph Convolutional Networks via Adaptive Filter Banks
Graph convolutional networks have been a powerful tool in representation learning of networked data.
All-optical graph representation learning using integrated diffractive photonic computing units
Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance.
LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learning
Subsequently, this local information is aligned and propagated to the preserved nodes to alleviate information loss in graph coarsening.
Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling
Specifically, adaptive spherical wavelets are learned with a lifting structure that consists of trainable lifting operators (i. e., update and predict operators).
Contrastive Regression for Domain Adaptation on Gaze Estimation
Appearance-based Gaze Estimation leverages deep neural networks to regress the gaze direction from monocular images and achieve impressive performance.
Optimization-based Block Coordinate Gradient Coding for Mitigating Partial Stragglers in Distributed Learning
To reduce computational complexity, we first transform each to an equivalent but much simpler discrete problem with N\llL variables representing the partition of the L coordinates into N blocks, each with identical redundancy.
Dual Contrastive Learning for Spatio-temporal Representation
In this way, the static scene and the dynamic motion are simultaneously encoded into the compact RGB representation.
Motion-inductive Self-supervised Object Discovery in Videos
In this paper, we consider the task of unsupervised object discovery in videos.
Ranked #3 on
Unsupervised Object Segmentation
on DAVIS 2016
Lightweight network towards real-time image denoising on mobile devices
In this paper, we identify the real bottlenecks that affect the CNN-based models' run-time performance on mobile devices: memory access cost and NPU-incompatible operations, and build the model based on these.
Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation
There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies.
Learned Lossless Compression for JPEG via Frequency-Domain Prediction
In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients.
Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networks
Due to the complex and changing interactions in dynamic scenarios, motion forecasting is a challenging problem in autonomous driving.
Ranked #1 on
Trajectory Prediction
on Argoverse2
Promoting Semantic Connectivity: Dual Nearest Neighbors Contrastive Learning for Unsupervised Domain Generalization
Then, we propose a novel unsupervised domain generalization approach, namely Dual Nearest Neighbors contrastive learning with strong Augmentation (DN^2A).
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model.
ActionPrompt: Action-Guided 3D Human Pose Estimation With Text and Pose Prompting
Recent 2D-to-3D human pose estimation (HPE) utilizes temporal consistency across sequences to alleviate the depth ambiguity problem but ignore the action related prior knowledge hidden in the pose sequence.
Towards Unsupervised Domain Generalization for Face Anti-Spoofing
In this paper, we propose the first Unsupervised Domain Generalization framework for Face Anti-Spoofing, namely UDG-FAS, which could exploit large amounts of easily accessible unlabeled data to learn generalizable features for enhancing the low-data regime of FAS.
Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views
We propose a cascade generation framework constructed with two Zero-1-to-3 models, named Cascade-Zero123, to tackle this issue, which progressively extracts 3D information from the source image.
Spatial-Temporal DAG Convolutional Networks for End-to-End Joint Effective Connectivity Learning and Resting-State fMRI Classification
To address these issues in an end-to-end manner, we model the brain network as a directed acyclic graph (DAG) to discover direct causal connections between brain regions and propose Spatial-Temporal DAG Convolutional Network (ST-DAGCN) to jointly infer effective connectivity and classify rs-fMRI time series by learning brain representations based on nonlinear structural equation model.
scBiGNN: Bilevel Graph Representation Learning for Cell Type Classification from Single-cell RNA Sequencing Data
A gene-level GNN is established to adaptively learn gene-gene interactions and cell representations via the self-attention mechanism, and a cell-level GNN builds on the cell-cell graph that is constructed from the cell representations generated by the gene-level GNN.
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
Vision-language foundation models, represented by Contrastive language-image pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks.
Measuring the Discrepancy between 3D Geometric Models using Directional Distance Fields
We then transfer the discrepancy between two 3D geometric models as the discrepancy between their DDFs defined on an identical domain, naturally establishing model correspondence.
