Search Results for author:
Found 101 papers, 26 papers with code
FTL: A universal framework for training low-bit DNNs via Feature Transfer
Compared with low-bit models trained directly, the proposed framework brings 0. 5% to 3. 4% accuracy gains to three different quantization schemes.
Guiding Text-to-Image Diffusion Model Towards Grounded Generation
The goal of this paper is to augment a pre-trained text-to-image diffusion model with the ability of open-vocabulary objects grounding, i. e., simultaneously generating images and segmentation masks for the corresponding visual entities described in the text prompt.
Integrating features from lymph node stations for metastatic lymph node detection
The branch targets to solve a closely related task on the LN station level, i. e., classifying whether an LN station contains metastatic LN or not, so as to learn representations for LN stations.
MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training
In this paper, we consider the problem of enhancing self-supervised visual-language pre-training (VLP) with medical-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice.
On Transforming Reinforcement Learning by Transformer: The Development Trajectory
Transformer, originally devised for natural language processing, has also attested significant success in computer vision.
Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization
And as a result, the dual-branch complementarity is effectively fused to promote a strong alliance.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation
However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous conditions.
Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models
When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks.
A Simple Plugin for Transforming Images to Arbitrary Scales
Existing models on super-resolution often specialized for one scale, fundamentally limiting their use in practical scenarios.
Transforming the Interactive Segmentation for Medical Imaging
The goal of this paper is to interactively refine the automatic segmentation on challenging structures that fall behind human performance, either due to the scarcity of available annotations or the difficulty nature of the problem itself, for example, on segmenting cancer or small organs.
Neural Message Passing for Visual Relationship Detection
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction
To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose features into richer graph spectrum bands.
Registration based Few-Shot Anomaly Detection
Inspired by how humans detect anomalies, i. e., comparing an image in question to normal images, we here leverage registration, an image alignment task that is inherently generalizable across categories, as the proxy task, to train a category-agnostic anomaly detection model.
Ranked #47 on
Anomaly Detection
on MVTec AD
Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting
Further, we apply the proposed framework to current SOTA multi-agent multi-modal forecasting systems as a plugin module, which enables the SOTA systems to 1) estimate the uncertainty in the multi-agent multi-modal trajectory forecasting task; 2) rank the multiple predictions and select the optimal one based on the estimated uncertainty.
Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoning
Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction.
Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
We present a simple yet effective self-supervised framework for audio-visual representation learning, to localize the sound source in videos.
K-Space Transformer for Undersampled MRI Reconstruction
This paper considers the problem of undersampled MRI reconstruction.
Contrastive Learning with Boosted Memorization
Different from previous works, we explore this direction from an alternative perspective, i. e., the data perspective, and propose a novel Boosted Contrastive Learning (BCL) method.
Self-Supervised Masking for Unsupervised Anomaly Detection and Localization
To extend the reconstruction-based anomaly detection architecture to the localized anomalies, we propose a self-supervised learning approach through random masking and then restoring, named Self-Supervised Masking (SSM) for unsupervised anomaly detection and localization.
GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning
From the aspect of interaction capturing, we propose a trainable multiscale hypergraph to capture both pair-wise and group-wise interactions at multiple group sizes.
Task Decoupled Framework for Reference-Based Super-Resolution
Those methods conduct the super-resolution task of the input low-resolution(LR) image and the texture transfer task from the reference image together in one module, easily introducing the interference between LR and reference features.
LAR-SR: A Local Autoregressive Model for Image Super-Resolution
Previous super-resolution (SR) approaches often formulate SR as a regression problem and pixel wise restoration, which leads to a blurry and unreal SR output.
Prompting Visual-Language Models for Efficient Video Understanding
Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation.
Ranked #2 on
Zero-Shot Action Detection
on ActivityNet-1.3
Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances.
Spatio-Temporal Graph Complementary Scattering Networks
Spatio-temporal graph signal analysis has a significant impact on a wide range of applications, including hand/body pose action recognition.
Click-through Rate Prediction with Auto-Quantized Contrastive Learning
Click-through rate (CTR) prediction becomes indispensable in ubiquitous web recommendation applications.
A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
To leverage the human body shape prior, LPNet exploits the topological information of the body mesh to learn an expressive visual representation for the target person in the 3D mesh space.
Self-supervised Tumor Segmentation through Layer Decomposition
In this paper, we target self-supervised representation learning for zero-shot tumor segmentation.
Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction
The core of MST-GNN is a multiscale spatio-temporal graph that explicitly models the relations in motions at various spatial and temporal scales.
CaT: Weakly Supervised Object Detection with Category Transfer
To handle overlapping category transfer, we propose a double-supervision mean teacher to gather common category information and bridge the domain gap between two datasets.
Cooperative Learning for Noisy Supervision
Learning with noisy labels has gained the enormous interest in the robust deep learning area.
MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets
A novel Multi-teacher Single-student Knowledge Distillation (MS-KD) framework is proposed, where the teacher models are pre-trained single-organ segmentation networks, and the student model is a multi-organ segmentation network.
Semi-supervised 3D Hand-Object Pose Estimation via Pose Dictionary Learning
Experiments are conducted on FPHA and HO-3D datasets.
Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network
This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system.
Knowledge distillation from multi-modal to mono-modal segmentation networks
In this paper, we propose KD-Net, a framework to transfer knowledge from a trained multi-modal network (teacher) to a mono-modal one (student).
A Fourier-based Framework for Domain Generalization
Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data.
Contrastive Attraction and Contrastive Repulsion for Representation Learning
We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.
Monitoring urban ecosystem service value using dynamic multi-level grids
Ecosystem valuation is a method of assigning a monetary value to an ecosystem with its goods and services, often referred to as ecosystem service value (ESV).
Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
To solve this issue, we introduce an adaptive mutual supervision framework (AMS) with two branches, where the base branch adopts CAS to localize the most discriminative action regions, while the supplementary branch localizes the less discriminative action regions through a novel adaptive sampler.
Ranked #5 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Collaborative Label Correction via Entropy Thresholding
Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels.
Spatio-Temporal Sparsification for General Robust Graph Convolution Networks
Graph Neural Networks (GNNs) have attracted increasing attention due to its successful applications on various graph-structure data.
Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining
(2) The sampled deep vertex features with positional embedding are mapped into a sequential space and decoded by a multilayer perceptron (MLP) for semantic classification.
Uncertainty-aware Incremental Learning for Multi-organ Segmentation
Specifically, given a pretrained $K$ organ segmentation model and a new single-organ dataset, we train a unified $K+1$ organ segmentation model without accessing any data belonging to the previous training stages.
Divide and Conquer for Single-Frame Temporal Action Localization
Single-frame temporal action localization (STAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance.
Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation
To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network.
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses
Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance.
Ranked #2 on
Weakly Supervised Action Localization
on BEOID
Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework
Based on this object function we introduce a novel information theoretic framework for unsupervised image anomaly detection.
Ranked #8 on
Anomaly Detection
on One-class CIFAR-100
ESAD: End-to-end Deep Semi-supervised Anomaly Detection
This paper explores semi-supervised anomaly detection, a more practical setting for anomaly detection where a small additional set of labeled samples are provided.
Ranked #24 on
Anomaly Detection
on One-class CIFAR-10
(using extra training data)
Privileged Knowledge Distillation for Online Action Detection
Knowledge distillation is employed to transfer the privileged information from the offline teacher to the online student.
Ranked #5 on
Online Action Detection
on TVSeries
Learning on Attribute-Missing Graphs
Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.
Sampling and Recovery of Graph Signals based on Graph Neural Networks
Compared to previous analytical sampling and recovery, the proposed methods are able to flexibly learn a variety of graph signal models from data by leveraging the learning ability of neural networks; compared to previous neural-network-based sampling and recovery, the proposed methods are designed through exploiting specific graph properties and provide interpretability.
Two-Stream Compare and Contrast Network for Vertebral Compression Fracture Diagnosis
In this paper, we explore to model VCFs diagnosis as a three-class classification problem, i. e. normal vertebrae, benign VCFs, and malignant VCFs.
SAR: Scale-Aware Restoration Learning for 3D Tumor Segmentation
We demonstrate the effectiveness of our methods on two downstream tasks: i) Brain tumor segmentation, ii) Pancreas tumor segmentation.
Graph Cross Networks with Vertex Infomax Pooling
Based on trainable hierarchical representations of a graph, GXN enables the interchange of intermediate features across scales to promote information flow.
Urban Traffic Flow Forecast Based on FastGCRNN
Traffic forecasting is an important prerequisite for the application of intelligent transportation systems in urban traffic networks.
Towards Equivalent Transformation of User Preferences in Cross Domain Recommendation
In this paper, we attempt to learn both features of user preferences in a more principled way.
Decoupled Variational Embedding for Signed Directed Networks
Comprehensive results on both link sign prediction and node recommendation task demonstrate the effectiveness of DVE.
Learning Robust Node Representations on Graphs
Graph neural networks (GNN), as a popular methodology for node representation learning on graphs, currently mainly focus on preserving the smoothness and identifiability of node representations.
Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph
Most existing methods focus on preserving the first-order proximity between entities in the KG.
Collaborative Adversarial Learning for RelationalLearning on Multiple Bipartite Graphs
The two-level alignment acts as two different constraints on different relations of the shared entities and facilitates better knowledge transfer for relational learning on multiple bipartite graphs.
Universal-to-Specific Framework for Complex Action Recognition
The U2S framework is composed of three subnetworks: a universal network, a category-specific network, and a mask network.
From Quantized DNNs to Quantizable DNNs
This paper proposes Quantizable DNNs, a special type of DNNs that can flexibly quantize its bit-width (denoted as `bit modes' thereafter) during execution without further re-training.
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning.
Collaborative Motion Prediction via Neural Motion Message Passing
Motion prediction is essential and challenging for autonomous vehicles and social robots.
Bottom-Up Temporal Action Localization with Mutual Regularization
To alleviate this problem, we introduce two regularization terms to mutually regularize the learning procedure: the Intra-phase Consistency (IntraC) regularization is proposed to make the predictions verified inside each phase; and the Inter-phase Consistency (InterC) regularization is proposed to keep consistency between these phases.
Attribute Restoration Framework for Anomaly Detection
We here propose to break this equivalence by erasing selected attributes from the original data and reformulate it as a restoration task, where the normal and the anomalous data are expected to be distinguishable based on restoration errors.
Ranked #20 on
Anomaly Detection
on One-class CIFAR-10
Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning
We here propose to model the dynamic process of iterative interactive image segmentation as a Markov decision process (MDP) and solve it with reinforcement learning (RL).
Cascading: Association Augmented Sequential Recommendation
Recently, recommendation according to sequential user behaviors has shown promising results in many application scenarios.
Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction
For the backbone, we propose multi-branch multi-scale graph convolution networks to extract spatial and temporal features.
Ranked #28 on
Skeleton Based Action Recognition
on NTU RGB+D
Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data
Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks.
Node Attribute Generation on Graphs
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
Defending Adversarial Attacks by Correcting logits
Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning.
Handwritten Chinese Font Generation with Collaborative Stroke Refinement
Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters.
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
We validate AS-GCN in action recognition using two skeleton data sets, NTU-RGB+D and Kinetics.
Safeguarded Dynamic Label Regression for Generalized Noisy Supervision
We further generalize LCCN for open-set noisy labels and the semi-supervised setting.
Ranked #33 on
Image Classification
on Clothing1M
(using extra training data)
Accelerate CNN via Recursive Bayesian Pruning
A new dropout-based measurement of redundancy, which facilitate the computation of posterior assuming inter-layer dependency, is introduced.
Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption
Unsupervised domain adaption aims to learn a powerful classifier for the target domain given a labeled source data set and an unlabeled target data set.
Phase Collaborative Network for Two-Phase Medical Image Segmentation
However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient.
Variational Collaborative Learning for User Probabilistic Representation
Conventional CF-based methods use the user-item interaction data as the sole information source to recommend items to users.
Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation.
Understanding VAEs in Fisher-Shannon Plane
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables.
A Unified Framework for Generalizable Style Transfer: Style and Content Separation
The encoders are expected to capture the underlying features for different styles and contents which is generalizable to new styles and contents.
Webpage Saliency Prediction with Two-stage Generative Adversarial Networks
Web page saliency prediction is a challenge problem in image transformation and computer vision.
Masking: A New Perspective of Noisy Supervision
It is important to learn various types of classifiers given training data with noisy labels.
Ranked #39 on
Image Classification
on Clothing1M
(using extra training data)
An Element Sensitive Saliency Model with Position Prior Learning for Web Pages
Understanding human visual attention is important for multimedia applications.
Variational Composite Autoencoders
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable.
Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
Convolution is spatially-symmetric, i. e., the visual features are independent of its position in the image, which limits its ability to utilize contextual cues for visual recognition.
Degeneration in VAE: in the Light of Fisher Information Loss
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representation learning.
Collaborative Learning for Weakly Supervised Object Detection
For object detection, taking WSDDN-like architecture as weakly supervised detector sub-network and Faster-RCNN-like architecture as strongly supervised detector sub-network, we propose an end-to-end Weakly Supervised Collaborative Detection Network.
Separating Style and Content for Generalized Style Transfer
We here attempt to separate the representations for styles and contents, and propose a generalized style transfer network consisting of style encoder, content encoder, mixer and decoder.
Chinese Typeface Transformation with Hierarchical Adversarial Network
Inspired by the recent advancement in Generative Adversarial Networks (GANs), we propose a Hierarchical Adversarial Network (HAN) for typeface transformation.
Deep Learning from Noisy Image Labels with Quality Embedding
However, the label noise among the datasets severely degenerates the \mbox{performance of deep} learning approaches.
Query-free Clothing Retrieval via Implicit Relevance Feedback
We model this problem as a new type of image retrieval task in which the target image resides only in the user's mind (called "mental image retrieval" hereafter).
Clothing Retrieval with Visual Attention Model
The VAM is further connected to a global network to form an end-to-end network structure through Impdrop connection which randomly Dropout on the feature maps with the probabilities given by the attention map.
Deep Hashing with Triplet Quantization Loss
While minimizing the quantization loss guarantees that quantization has minimal effect on retrieval accuracy, it unfortunately significantly reduces the expressiveness of features even before the quantization.
SORT: Second-Order Response Transform for Visual Recognition
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks.
Deep Collaborative Learning for Visual Recognition
We formulate the function of a convolutional layer as learning a large visual vocabulary, and propose an alternative way, namely Deep Collaborative Learning (DCL), to reduce the computational complexity.
Unsupervised Triplet Hashing for Fast Image Retrieval
Considering the difficulty in obtaining labeled datasets for image retrieval task in large scale, we propose a novel CNN-based unsupervised hashing method, namely Unsupervised Triplet Hashing (UTH).
Part-Stacked CNN for Fine-Grained Visual Categorization
In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy.
Ranked #58 on
Fine-Grained Image Classification
on CUB-200-2011
Augmenting Strong Supervision Using Web Data for Fine-Grained Categorization
We propose a new method for fine-grained object recognition that employs part-level annotations and deep convolutional neural networks (CNNs) in a unified framework.
Multi-Touch Attribution in Online Advertising with Survival Theory
With the ever enhanced capability to tracking advertisement and users' interaction with the advertisement, data-driven multi-touch attribution models, which attempt to infer the contribution from user interaction data, become an important research direction.
