Search Results for author:
Found 96 papers, 52 papers with code
Deep Transferring Quantization
Specifically, we propose a method named deep transferring quantization (DTQ) to effectively exploit the knowledge in a pre-trained full-precision model.
Towards Stable Test-Time Adaptation in Dynamic Wild World
In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability.
Automatic Subspace Evoking for Efficient Neural Architecture Search
Then, we perform a local search within the evoked subspace to find an effective architecture.
Ranked #2 on
Neural Architecture Search
on NAS-Bench-201, ImageNet-16-120
(Accuracy (Val) metric)
Learning Active Camera for Multi-Object Navigation
How to make robots perceive the environment as efficiently as humans is a fundamental problem in robotics.
Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
To achieve accurate and efficient navigation, it is critical to build a map that accurately represents both spatial location and the semantic information of the environment objects.
Pareto-aware Neural Architecture Generation for Diverse Computational Budgets
More critically, these independent search processes cannot share their learned knowledge (i. e., the distribution of good architectures) with each other and thus often result in limited search results.
Masked Motion Encoding for Self-Supervised Video Representation Learning
The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.
Ranked #1 on
Self-Supervised Action Recognition
on UCF101
Multi-Scale Multi-Target Domain Adaptation for Angle Closure Classification
Based on these domain-invariant features at different scales, the deep model trained on the source domain is able to classify angle closure on multiple target domains even without any annotations in these domains.
Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle
Inspired by this observation, we propose diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty.
DAS: Densely-Anchored Sampling for Deep Metric Learning
To this end, we propose a Densely-Anchored Sampling (DAS) scheme that considers the embedding with corresponding data point as "anchor" and exploits the anchor's nearby embedding space to densely produce embeddings without data points.
Ranked #2 on
Metric Learning
on CUB-200-2011
Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
2) Prototype-based alignment and replay: based on the identified label prototypes, we align both domains and enforce the model to retain previous knowledge.
Towards Lightweight Super-Resolution with Dual Regression Learning
Nevertheless, it is hard for existing model compression methods to accurately identify the redundant components due to the extremely large SR mapping space.
Efficient Test-Time Model Adaptation without Forgetting
Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w. r. t.
Boost Test-Time Performance with Closed-Loop Inference
Motivated by this, we propose to predict those hard-classified test samples in a looped manner to boost the model performance.
Debiased Visual Question Answering from Feature and Sample Perspectives
From the sample perspective, we construct two types of negative samples to assist the training of the models, without introducing additional annotations.
Graph Convolutional Module for Temporal Action Localization in Videos
To this end, we propose a general graph convolutional module (GCM) that can be easily plugged into existing action localization methods, including two-stage and one-stage paradigms.
Ranked #2 on
Temporal Action Localization
on THUMOS’14
(mAP IOU@0.1 metric)
V2C: Visual Voice Cloning
Existing Voice Cloning (VC) tasks aim to convert a paragraph text to a speech with desired voice specified by a reference audio.
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
State-of-the-art methods largely rely on a general pipeline that first learns point-wise features discriminative at semantic and instance levels, followed by a separate step of point grouping for proposing object instances.
Ranked #5 on
3D Instance Segmentation
on ScanNet(v2)
Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints
More critically, EAS is able to find compact architectures within 0. 1 second for 50 deployment scenarios.
AdaXpert: Adapting Neural Architecture for Growing Data
To address this, we present a neural architecture adaptation method, namely Adaptation eXpert (AdaXpert), to efficiently adjust previous architectures on the growing data.
Content-Aware Convolutional Neural Networks
In practice, the convolutional operation on some of the windows (e. g., smooth windows that contain very similar pixels) can be very redundant and may introduce noises into the computation.
Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation
In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) to exploit perceptual information from two modalities, namely, appearance information from RGB images and spatio-depth information from point clouds.
Ranked #11 on
LIDAR Semantic Segmentation
on nuScenes
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
(2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes.
Ranked #9 on
Domain Adaptation
on VisDA2017
ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
Specifically, we propose two tasks to learn the appearance and speed consistency, respectively.
Towards Accurate Text-based Image Captioning with Content Diversity Exploration
This task, however, is very challenging because an image often contains complex texts and visual information that is hard to be described comprehensively.
Learning Defense Transformers for Counterattacking Adversarial Examples
Relying on this, we learn a defense transformer to counterattack the adversarial examples by parameterizing the affine transformations and exploiting the boundary information of DNNs.
Internal Wasserstein Distance for Adversarial Attack and Defense
Existing attack methods often construct adversarial examples relying on some metrics like the $\ell_p$ distance to perturb samples.
Contrastive Neural Architecture Search with Neural Architecture Comparators
One of the key steps in Neural Architecture Search (NAS) is to estimate the performance of candidate architectures.
Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets
To this end, we propose a Pareto-Frontier-aware Neural Architecture Generator (NAG) which takes an arbitrary budget as input and produces the Pareto optimal architecture for the target budget.
Towards Accurate and Compact Architectures via Neural Architecture Transformer
To address this issue, we propose a Neural Architecture Transformer++ (NAT++) method which further enlarges the set of candidate transitions to improve the performance of architecture optimization.
Deep View Synthesis via Self-Consistent Generative Network
To address the above issues, in this paper, we propose a novel deep generative model, called Self-Consistent Generative Network (SCGN), which synthesizes novel views from the given input views without explicitly exploiting the geometric information.
Single-path Bit Sharing for Automatic Loss-aware Model Compression
By jointly training the binary gates in conjunction with network parameters, the compression configurations of each layer can be automatically determined.
How to Train Your Agent to Read and Write
Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice.
Ranked #3 on
KG-to-Text Generation
on AGENDA
Pareto-Frontier-aware Neural Architecture Search
To find promising architectures under different budgets, existing methods may have to perform an independent search for each budget, which is very inefficient and unnecessary.
Modular Graph Attention Network for Complex Visual Relational Reasoning
Moreover, to capture the complex logic in a query, we construct a relational graph to represent the visual objects and their relationships, and propose a multi-step reasoning method to progressively understand the complex logic.
Ranked #2 on
Referring Expression Comprehension
on CLEVR-Ref+
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition.
Ranked #7 on
Self-Supervised Action Recognition
on UCF101
Double Forward Propagation for Memorized Batch Normalization
Although the standard BN can significantly accelerate the training of DNNs and improve the generalization performance, it has several underlying limitations which may hamper the performance in both training and inference.
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification
Unlike previous methods, we for the first time propose a generic gait encoding approach that can utilize unlabeled skeleton data to learn gait representations in a self-supervised manner.
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images
However, they all have their own drawbacks, and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topologicalstructures in their learning frameworks.
Location-aware Graph Convolutional Networks for Video Question Answering
In this work, we propose to represent the contents in the video as a location-aware graph by incorporating the location information of an object into the graph construction.
Improving Generative Adversarial Networks with Local Coordinate Coding
In this paper, rather than sampling from the predefined prior distribution, we propose an LCCGAN model with local coordinate coding (LCC) to improve the performance of generating data.
Length-Controllable Image Captioning
We verify the merit of the proposed length level embedding on three models: two state-of-the-art (SOTA) autoregressive models with different types of decoder, as well as our proposed non-autoregressive model, to show its generalization ability.
Retinal Image Segmentation with a Structure-Texture Demixing Network
Retinal image segmentation plays an important role in automatic disease diagnosis.
Generating Visually Aligned Sound from Videos
During testing, the audio forwarding regularizer is removed to ensure that REGNET can produce purely aligned sound only from visual features.
AQD: Towards Accurate Quantized Object Detection
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices.
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search
With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method significantly improves the search efficiency and finds better architectures than existing NAS methods.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
Deep learning based medical image diagnosis has shown great potential in clinical medicine.
Relation-Aware Transformer for Portfolio Policy Learning
One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions.
A Real-time Action Representation with Temporal Encoding and Deep Compression
Our method achieves clear improvements on UCF101 action recognition benchmark against state-of-the-art real-time methods by 5. 4% in terms of accuracy and 2 times faster in terms of inference speed with a less than 5MB storage model.
AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography
To address this, we organized the Angle closure Glaucoma Evaluation challenge (AGE), held in conjunction with MICCAI 2019.
COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
There are two main challenges: 1) the discrepancy of data distributions between domains; 2) the task difference between the diagnosis of typical pneumonia and COVID-19.
Dense Regression Network for Video Grounding
The key idea of this paper is to use the distances between the frame within the ground truth and the starting (ending) frame as dense supervisions to improve the video grounding accuracy.
Natural Language Moment Retrieval
Natural Language Queries
+2
A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
In this paper, we aim to review various adversarial attack and defense methods on chest X-rays.
Disturbance-immune Weight Sharing for Neural Architecture Search
To alleviate the performance disturbance issue, we propose a new disturbance-immune update strategy for model updating.
Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution
Extensive experiments with paired training data and unpaired real-world data demonstrate our superiority over existing methods.
Generative Low-bitwidth Data Free Quantization
More critically, our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method.
Ranked #1 on
Data Free Quantization
on ImageNet
(ImageNet W8A8 Top-1 Accuracy metric)
Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning
This task, however, has two main difficulties: (i) the non-stationary price series and complex asset correlations make the learning of feature representation very hard; (ii) the practicality principle in financial markets requires controlling both transaction and risk costs.
Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
To this end, we propose a House Plan Generative Model (HPGM) that first translates the language input to a structural graph representation and then predicts the layout of rooms with a Graph Conditioned Layout Prediction Network (GC LPN) and generates the interior texture with a Language Conditioned Texture GAN (LCT-GAN).
Joint Wasserstein Distribution Matching
However, the resultant optimization problem is still intractable.
Discrimination-aware Network Pruning for Deep Model Compression
In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power.
Online Adaptive Asymmetric Active Learning with Limited Budgets
In these problems, there are two key challenges: the query budget is often limited; the ratio between classes is highly imbalanced.
Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
In this paper, we seek to exploit rich labeled data from relevant domains to help the learning in the target task with unsupervised domain adaptation (UDA).
Multi-marginal Wasserstein GAN
Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation.
NAT: Neural Architecture Transformer for Accurate and Compact Architectures
To verify the effectiveness of the proposed strategies, we apply NAT on both hand-crafted architectures and NAS based architectures.
Towards Interpreting Deep Neural Networks via Understanding Layer Behaviors
ii) the $W$-distance of a specific layer to the target distribution tends to decrease along training iterations.
Structured Binary Neural Networks for Image Recognition
Experiments on both classification, semantic segmentation and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature.
Graph Convolutional Networks for Temporal Action Localization
Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization.
Ranked #4 on
Temporal Action Localization
on THUMOS’14
(mAP IOU@0.1 metric)
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric, using extra
training data)
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
Furthermore, we propose a second progressive quantization scheme which gradually decreases the bit-width from high-precision to low-precision during training.
Attention Guided Network for Retinal Image Segmentation
Learning structural information is critical for producing an ideal result in retinal image segmentation.
Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction
We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective.
Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers
Such a perspective enables us to study deep multi-view learning in the context of regularized network training, for which we present control experiments of benchmark image classification to show the efficacy of our proposed CorrReg.
Domain-Symmetric Networks for Adversarial Domain Adaptation
Since target samples are unlabeled, we also propose a scheme of cross-domain training to help learn the target classifier.
Training Quantized Neural Networks with a Full-precision Auxiliary Module
In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function.
Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
To address this issue, we develop a novel GAN called Auto-Embedding Generative Adversarial Network (AEGAN), which simultaneously encodes the global structure features and captures the fine-grained details.
You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
Most state-of-the-art methods in VG operate in a two-stage manner, wherein the first stage an object detector is adopted to generate a set of object proposals from the input image and the second stage is simply formulated as a cross-modal matching problem that finds the best match between the language query and all region proposals.
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically} for mobile devices with limited power capacity and computation resources.
Discrimination-aware Channel Pruning for Deep Neural Networks
Channel pruning is one of the predominant approaches for deep model compression.
MPTV: Matching Pursuit Based Total Variation Minimization for Image Deconvolution
Compared to existing methods, MPTV is less sensitive to the choice of the trade-off parameter between data fitting and regularization.
Learning Joint Wasserstein Auto-Encoders for Joint Distribution Matching
We study the joint distribution matching problem which aims at learning bidirectional mappings to match the joint distribution of two domains.
Unsupervised Image-To-Image Translation
Video Frame Interpolation
+1
Dual Reconstruction Nets for Image Super-Resolution with Gradient Sensitive Loss
However, most deep learning methods employ feed-forward architectures, and thus the dependencies between LR and HR images are not fully exploited, leading to limited learning performance.
Adversarial Learning with Local Coordinate Coding
Generative adversarial networks (GANs) aim to generate realistic data from some prior distribution (e. g., Gaussian noises).
Visual Grounding via Accumulated Attention
There are three main challenges in VG: 1) what is the main focus in a query; 2) how to understand an image; 3) how to locate an object.
Multi-modality Sensor Data Classification with Selective Attention
Multimodal wearable sensor data classification plays an important role in ubiquitous computing and has a wide range of applications in scenarios from healthcare to entertainment.
Adaptive Cost-sensitive Online Classification
Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost.
Towards Effective Low-bitwidth Convolutional Neural Networks
This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations.
Self-Paced Kernel Estimation for Robust Blind Image Deblurring
Rather than attempt to identify outliers to the model a priori, we instead propose to sequentially identify inliers, and gradually incorporate them into the estimation process.
The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs
As a result, the representation power of intermediate layers can be very weak and the model becomes very redundant with limited performance.
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization
Trace-norm regularization plays an important role in many areas such as machine learning and computer vision.
Fast Algorithms for Linear and Kernel SVM+
The SVM+ approach has shown excellent performance in visual recognition tasks for exploiting privileged information in the training data.
Blind Image Deconvolution by Automatic Gradient Activation
We show here that a subset of the image gradients are adequate to estimate the blur kernel robustly, no matter the gradient image is sparse or not.
Learning Graph Structure for Multi-Label Image Classification via Clique Generation
Exploiting label dependency for multi-label image classification can significantly improve classification performance.
Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR).
Matching Pursuit LASSO Part II: Applications and Sparse Recovery over Batch Signals
Matching Pursuit LASSIn Part I \cite{TanPMLPart1}, a Matching Pursuit LASSO ({MPL}) algorithm has been presented for solving large-scale sparse recovery (SR) problems.
Towards Ultrahigh Dimensional Feature Selection for Big Data
In this paper, we present a new adaptive feature scaling scheme for ultrahigh-dimensional feature selection on Big Data.
