Search Results for author:
Found 108 papers, 44 papers with code
Exploring the Robustness of Human Parsers Towards Common Corruptions
The experimental results show that the proposed method demonstrates good universality which can improve the robustness of the human parsing models and even the semantic segmentation models when facing various image common corruptions.
Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging
In this paper, we conduct a comprehensive study of over 10 fast adversarial training methods in terms of adversarial robustness and training costs.
Privacy-Enhancing Face Obfuscation Guided by Semantic-Aware Attribution Maps
Within this module, we introduce a pixel importance estimation model based on Shapley value to obtain a pixel-level attribution map, and then each pixel on the attribution map is aggregated into semantic facial parts, which are used to quantify the importance of different facial parts.
Reversible Quantization Index Modulation for Static Deep Neural Network Watermarking
In this paper, we propose a novel RDH-based static DNN watermarking scheme using quantization index modulation (QIM).
Towards an Accurate and Secure Detector against Adversarial Perturbations
It expands the above works on two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability and thereby is more suitable for capturing adversarial patterns than the common trigonometric or wavelet basis; 2) the extensive parameters for decomposition are generated by a pseudo-random function with secret keys, hence blocking the defense-aware adversarial attack.
Inter-frame Accelerate Attack against Video Interpolation Models
We apply adversarial attacks to VIF models and find that the VIF models are very vulnerable to adversarial examples.
FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature
Federated learning allows multiple parties to collaborate in learning a global model without revealing private data.
FedZKP: Federated Model Ownership Verification with Zero-knowledge Proof
Federated learning (FL) allows multiple parties to cooperatively learn a federated model without sharing private data with each other.
LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity
Motivated by it, we propose to use the local similarity (LocalSim) to learn node-level weighted fusion, which can also serve as a plug-and-play module.
Cognition Guided Human-Object Relationship Detection
Human-object relationship detection reveals the fine-grained relationship between humans and objects, helping the comprehensive understanding of videos.
Selective Frequency Network for Image Restoration
Image restoration aims to reconstruct the latent sharp image from its corrupted counterpart.
Ranked #1 on
Image Dehazing
on SOTS Outdoor
Improving Fast Adversarial Training with Prior-Guided Knowledge
This initialization is generated by using high-quality adversarial perturbations from the historical training process.
Representing Noisy Image Without Denoising
In this paper, we explore a non-learning paradigm that aims to derive robust representation directly from noisy images, without the denoising as pre-processing.
Focal Network for Image Restoration
Image restoration aims to reconstruct a sharp image from its degraded counterpart, which plays an important role in many fields.
Lightweight Image Super-Resolution with Superpixel Token Interaction
Our method employs superpixels to cluster local similar pixels to form the explicable local regions and utilizes intra-superpixel attention to enable local information interaction.
A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal
Second, we discuss the challenges of face restoration.
Rethinking Image Restoration for Object Detection
To address the issue, we propose a targeted adversarial attack in the restoration procedure to boost object detection performance after restoration.
Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning
Compared to the state-of-the-art reinforcement learning method, our model's network parameters are reduced to only 37\% of theirs, and the solution gap of our model towards the expert solutions decreases from 6. 8\% to 1. 3\% on average.
OpenAUC: Towards AUC-Oriented Open-Set Recognition
In this paper, a systematic analysis reveals that most existing metrics are essentially inconsistent with the aforementioned goal of OSR: (1) For metrics extended from close-set classification, such as Open-set F-score, Youden's index, and Normalized Accuracy, a poor open-set prediction can escape from a low performance score with a superior close-set prediction.
CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection
Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the novel cross-modality interaction and refinement.
A Unified Framework against Topology and Class Imbalance
We develop a multi-class AUC optimization work to deal with the class imbalance problem.
The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm
Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering.
MaxMatch: Semi-Supervised Learning with Worst-Case Consistency
In recent years, great progress has been made to incorporate unlabeled data to overcome the inefficiently supervised problem via semi-supervised learning (SSL).
Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
Specifically, we propose a sample-specific data augmentation to transfer the teacher model's ability in capturing distinct frequency components and suggest an adversarial feature augmentation to extract the teacher model's perceptions of non-robust features in the data.
A Large-scale Multiple-objective Method for Black-box Attack against Object Detection
Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information.
A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game
From the perspective of the dynamical system, the attack behavior with a target ranking list is a fixed point belonging to the composition of the adversary and the victim.
Sim2Word: Explaining Similarity with Representative Attribute Words via Counterfactual Explanations
Different from existing models, in this paper, we propose a new interpretation method that explains the image similarity models by salience maps and attribute words.
Optimizing Partial Area Under the Top-k Curve: Theory and Practice
Finally, the experimental results on four benchmark datasets validate the effectiveness of our proposed framework.
MOVE: Effective and Harmless Ownership Verification via Embedded External Features
In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features.
Prior-Guided Adversarial Initialization for Fast Adversarial Training
Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process.
Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal
Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good.
AIParsing: Anchor-free Instance-level Human Parsing
Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level.
Geometry Interaction Knowledge Graph Embeddings
Knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks.
Optimizing Two-way Partial AUC with an End-to-end Framework
The critical challenge along this course lies in the difficulty of performing gradient-based optimization with end-to-end stochastic training, even with a proper choice of surrogate loss.
Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
However, in this work, by taking a theoretical analysis, we find that negative sampling would lead to a biased estimation of the generalization error.
Entity-Graph Enhanced Cross-Modal Pretraining for Instance-level Product Retrieval
Our goal in this research is to study a more realistic environment in which we can conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories.
ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learning
Semi-Supervised Learning (SSL) has advanced classification tasks by inputting both labeled and unlabeled data to train a model jointly.
Detecting Recolored Image by Spatial Correlation
In this paper, we try to explore a solution from the perspective of the spatial correlation, which exhibits the generic detection capability for both conventional and deep learning-based recoloring.
LAS-AT: Adversarial Training with Learnable Attack Strategy
In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness.
A Principled Design of Image Representation: Towards Forensic Tasks
Image forensics is a rising topic as the trustworthy multimedia content is critical for modern society.
Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection
Extensive experiments demonstrate that our method can effectively and efficiently attack various popular object detectors, including anchor-based and anchor-free, and generate transferable adversarial examples.
Defending against Model Stealing via Verifying Embedded External Features
In this paper, we explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified \emph{external features}.
Diverse Message Passing for Attribute with Heterophily
Based on this attribute homophily rate, we propose a Diverse Message Passing (DMP) framework, which specifies every attribute propagation weight on each edge.
Implicit Feedbacks are Not Always Favorable: Iterative Relabeled One-Class Collaborative Filtering against Noisy Interactions
As the core of the framework, the iterative relabeling module exploits the self-training principle to dynamically generate pseudo labels for user preferences.
Boosting Fast Adversarial Training with Learnable Adversarial Initialization
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training.
An Effective and Robust Detector for Logo Detection
Moreover, we have applied the proposed methods to competition ACM MM2021 Robust Logo Detection that is organized by Alibaba on the Tianchi platform and won top 2 in 36489 teams.
Learning with Multiclass AUC: Theory and Algorithms
Our foundation is based on the M metric, which is a well-known multiclass extension of AUC.
Comprehensive Studies for Arbitrary-shape Scene Text Detection
In this paper, we carefully examine and analyze the inconsistent settings, and propose a unified framework for the bottom-up based scene text detection methods.
Poisoning Attack against Estimating from Pairwise Comparisons
In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attacks on pairwise ranking algorithms, which can be formalized as the dynamic and static games between the ranker and the attacker and can be modeled as certain kinds of integer programming problems.
Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning
To address the problem, we propose a novel network capable of real-time dehazing of 4K images on a single GPU, which consists of three deep CNNs.
Progressive Contour Regression for Arbitrary-Shape Scene Text Detection
In the second stage, the contours of the oriented text proposals are iteratively regressed to arbitrarily shaped ones.
Generate More Imperceptible Adversarial Examples for Object Detection
The existing attack methods have the following problems: 1) the training generator takes a long time and is difficult to extend to a large dataset; 2) the excessive destruction of the image features does not improve the black-box attack effect(the generated adversarial examples have poor transferability) and brings about visible perturbations.
SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation
Moreover, we release a new solar cell EL image dataset named as EL-2019, which includes three types of images: crack, finger interruption and defect-free.
A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
Image representation is an important topic in computer vision and pattern recognition.
Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring
Although recent research has witnessed a significant progress on the video deblurring task, these methods struggle to reconcile inference efficiency and visual quality simultaneously, especially on ultra-high-definition (UHD) videos (e. g., 4K resolution).
Ultra-High-Definition Image HDR Reconstruction via Collaborative Bilateral Learning
First, we propose a dual-path network to extract content and chromatic features at a reduced resolution of the low dynamic range (LDR) input.
Pyramid Architecture Search for Real-Time Image Deblurring
Multi-scale and multi-patch deep models have been shown effective in removing blurs of dynamic scenes.
Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem.
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes.
Single Image Super-Resolution via a Holistic Attention Network
Informative features play a crucial role in the single image super-resolution task.
Ranked #2 on
Image Super-Resolution
on Urban100 - 8x upscaling
Efficient Adversarial Attacks for Visual Object Tracking
In this paper, we analyze the weakness of object trackers based on the Siamese network and then extend adversarial examples to visual object tracking.
Face Super-Resolution Guided by 3D Facial Priors
State-of-the-art face super-resolution methods employ deep convolutional neural networks to learn a mapping between low- and high- resolution facial patterns by exploring local appearance knowledge.
Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction
To this end, we propose a novel multi-task learning method called Task-Feature Collaborative Learning (TFCL).
DM2C: Deep Mixed-Modal Clustering
Instead of transforming all the samples into a joint modality-independent space, our framework learns the mappings across individual modal spaces by virtue of cycle-consistency.
Generalized Block-Diagonal Structure Pursuit: Learning Soft Latent Task Assignment against Negative Transfer
Different from most of the previous work, pursuing the Block-Diagonal structure of LTAM (assigning latent tasks to output tasks) alleviates negative transfer via collaboratively grouping latent tasks and output tasks such that inter-group knowledge transfer and sharing is suppressed.
Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.
iSplit LBI: Individualized Partial Ranking with Ties via Split LBI
In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective.
Identifying and Resisting Adversarial Videos Using Temporal Consistency
We propose the temporal defense, which reconstructs the polluted frames with their temporally neighbor clean frames, to deal with the adversarial videos with sparse polluted frames.
Learning Personalized Attribute Preference via Multi-task AUC Optimization
Traditionally, most of the existing attribute learning methods are trained based on the consensus of annotations aggregated from a limited number of annotators.
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.
Deep Robust Subjective Visual Property Prediction in Crowdsourcing
The problem of estimating subjective visual properties (SVP) of images (e. g., Shoes A is more comfortable than B) is gaining rising attention.
Robust Ordinal Embedding from Contaminated Relative Comparisons
Existing ordinal embedding methods usually follow a two-stage routine: outlier detection is first employed to pick out the inconsistent comparisons; then an embedding is learned from the clean data.
Less but Better: Generalization Enhancement of Ordinal Embedding via Distributional Margin
To address the issue of insufficient training samples, we propose a margin distribution learning paradigm for ordinal embedding, entitled Distributional Margin based Ordinal Embedding (\textit{DMOE}).
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework.
ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples
In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier.
Transferable Adversarial Attacks for Image and Video Object Detection
Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection.
HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images
In this paper, we propose a novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement.
A Margin-based MLE for Crowdsourced Partial Ranking
A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order.
Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image
Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region.
Gated Fusion Network for Single Image Dehazing
The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder.
Ranked #16 on
Image Dehazing
on SOTS Outdoor
From Social to Individuals: a Parsimonious Path of Multi-level Models for Crowdsourced Preference Aggregation
In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or social utility function which generates their comparison behaviors in experiments.
Fake Colorized Image Detection
Based on our observations, i. e., potential traces in the hue, saturation, dark and bright channels, we propose two simple yet effective detection methods for fake colorized images: Histogram based Fake Colorized Image Detection (FCID-HIST) and Feature Encoding based Fake Colorized Image Detection (FCID-FE).
Multimedia
Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation
The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function.
Ranked #4 on
Optic Disc Segmentation
on REFUGE
From Common to Special: When Multi-Attribute Learning Meets Personalized Opinions
However, both categories ignore the joint effect of the two mentioned factors: the personal diversity with respect to the global consensus; and the intrinsic correlation among multiple attributes.
Stochastic Non-convex Ordinal Embedding with Stabilized Barzilai-Borwein Step Size
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years.
An Iterative Co-Saliency Framework for RGBD Images
In this paper, we propose an iterative RGBD co-saliency framework, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle model.
Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusion
Stereoscopic perception is an important part of human visual system that allows the brain to perceive depth.
Co-saliency Detection for RGBD Images Based on Multi-constraint Feature Matching and Cross Label Propagation
Different from the most existing co-saliency methods focusing on RGB images, this paper proposes a novel co-saliency detection model for RGBD images, which utilizes the depth information to enhance identification of co-saliency.
Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel
We analyze the relationship between motion blur trajectory and optical flow, and present a novel pixel-wise non-linear kernel model to account for motion blur.
Latent Multi-View Subspace Clustering
In this paper, we propose a novel Latent Multi-view Subspace Clustering (LMSC) method, which clusters data points with latent representation and simultaneously explores underlying complementary information from multiple views.
Binarized Mode Seeking for Scalable Visual Pattern Discovery
Second, we further extend bMS to a more general form, namely contrastive binary mean shift (cbMS), which maximizes the contrastive density in binary space, for finding informative patterns that are both frequent and discriminative for the dataset.
Image Deblurring via Extreme Channels Prior
The proposed method takes advantage of both Bright and Dark Channel Prior.
Cascade one-vs-rest detection network for fine-grained recognition without part annotations
To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories.
Parsimonious Mixed-Effects HodgeRank for Crowdsourced Preference Aggregation
In crowdsourced preference aggregation, it is often assumed that all the annotators are subject to a common preference or utility function which generates their comparison behaviors in experiments.
CUNet: A Compact Unsupervised Network for Image Classification
In this paper, we propose a compact network called CUNet (compact unsupervised network) to counter the image classification challenge.
A Hierarchical Distributed Processing Framework for Big Image Data
The proposed ICP framework consists of two mechanisms, i. e. SICP (Static ICP) and DICP (Dynamic ICP).
SketchNet: Sketch Classification With Web Images
In this study, we present a weakly supervised approach that discovers the discriminative structures of sketch images, given pairs of sketch images and web images.
Structural Correlation Filter for Robust Visual Tracking
In this paper, we propose a novel structural correlation filter (SCF) model for robust visual tracking.
False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking
With the rapid growth of crowdsourcing platforms it has become easy and relatively inexpensive to collect a dataset labeled by multiple annotators in a short time.
Makeup like a superstar: Deep Localized Makeup Transfer Network
In this paper, we propose a novel Deep Localized Makeup Transfer Network to automatically recommend the most suitable makeup for a female and synthesis the makeup on her face.
Quadratic Projection Based Feature Extraction with Its Application to Biometric Recognition
This paper presents a novel quadratic projection based feature extraction framework, where a set of quadratic matrices is learned to distinguish each class from all other classes.
Low-Rank Tensor Constrained Multiview Subspace Clustering
We introduce a low-rank tensor constraint to explore the complementary information from multiple views and, accordingly, establish a novel method called Low-rank Tensor constrained Multiview Subspace Clustering (LT-MSC).
Diversity-Induced Multi-View Subspace Clustering
In this paper, we focus on how to boost the multi-view clustering by exploring the complementary information among multi-view features.
Matching-CNN Meets KNN: Quasi-Parametric Human Parsing
Under the classic K Nearest Neighbor (KNN)-based nonparametric framework, the parametric Matching Convolutional Neural Network (M-CNN) is proposed to predict the matching confidence and displacements of the best matched region in the testing image for a particular semantic region in one KNN image.
Evaluating Visual Properties via Robust HodgeRank
In this paper we study the problem of how to estimate such visual properties from a ranking perspective with the help of the annotators from online crowdsourcing platforms.
Sparse Dictionary Learning for Edit Propagation of High-Resolution Images
Previous approaches for edit propagation typically employ a global optimization over the whole set of image pixels, incurring a prohibitively high memory and time consumption for high-resolution images.
Robust Separation of Reflection from Multiple Images
When one records a video/image sequence through a transparent medium (e. g. glass), the image is often a superposition of a transmitted layer (scene behind the medium) and a reflected layer.
Video Editing with Temporal, Spatial and Appearance Consistency
Given an area of interest in a video sequence, one may want to manipulate or edit the area, e. g. remove occlusions from or replace with an advertisement on it.
