Search Results for author:
Found 104 papers, 55 papers with code
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks.
Perceptual Image Compression with Cooperative Cross-Modal Side Information
The explosion of data has resulted in more and more associated text being transmitted along with images.
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression.
GMMFormer: Gaussian-Mixture-Model based Transformer for Efficient Partially Relevant Video Retrieval
In addition, PRVR methods ignore semantic differences between text queries relevant to the same video, leading to a sparse embedding space.
WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting
Recent CNN and Transformer-based models tried to utilize frequency and periodicity information for long-term time series forecasting.
Towards Robust Model Watermark via Reducing Parametric Vulnerability
To protect the copyright of DNNs, backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model by embedding a specific backdoor behavior before releasing it.
MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation
We propose MISSRec, a multi-modal pre-training and transfer learning framework for SR. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests while a novel interest-aware decoder is developed to grasp item-modality-interest relations for better sequence representation.
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.
GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization
Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server.
One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer
Current solutions for low-resolution text recognition (LTR) typically rely on a two-stage pipeline that involves super-resolution as the first stage followed by the second-stage recognition.
Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement
Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success.
TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale
We argue that tuning a text encoder end-to-end, as done in previous work, is suboptimal since it may overfit in terms of styles, thereby losing its original generalization ability to capture the semantics of various language registers.
Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding
In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks.
Backdoor Attack with Sparse and Invisible Trigger
More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack.
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
The exploration problem is one of the main challenges in deep reinforcement learning (RL).
Ranked #1 on
Atari Games
on Atari-57
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers
In this work, the VQVAE focus on feature extraction and reconstruction of images, and the transformers fit the manifold and locate anomalies in the latent space.
Backdoor Defense via Adaptively Splitting Poisoned Dataset
With the split clean data pool and polluted data pool, ASD successfully defends against backdoor attacks during training.
Delving into Identify-Emphasize Paradigm for Combating Unknown Bias
For challenge B, we point out that the gradient contribution statistics can be a reliable indicator to inspect whether the optimization is dominated by bias-aligned samples.
BackdoorBox: A Python Toolbox for Backdoor Learning
Third-party resources ($e. g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat.
DELTA: degradation-free fully test-time adaptation
However, we find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning.
Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model
Unsupervised surface anomaly detection aims at discovering and localizing anomalous patterns using only anomaly-free training samples.
Untargeted Backdoor Attack against Object Detection
The backdoored model has promising performance in predicting benign samples, whereas its predictions can be maliciously manipulated by adversaries based on activating its backdoors with pre-defined trigger patterns.
Backdoor Defense via Suppressing Model Shortcuts
Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process.
BATT: Backdoor Attack with Transformation-based Triggers
The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process.
Towards Mitigating the Problem of Insufficient and Ambiguous Supervision in Online Crowdsourcing Annotation
In real-world crowdsourcing annotation systems, due to differences in user knowledge and cultural backgrounds, as well as the high cost of acquiring annotation information, the supervision information we obtain might be insufficient and ambiguous.
Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
Most existing methods mainly focus on extracting global features from tampered images, while neglecting the relationships of local features between tampered and authentic regions within a single tampered image.
Vertical Semi-Federated Learning for Efficient Online Advertising
Specifically, we build an inference-efficient single-party student model applicable to the whole sample space and meanwhile maintain the advantage of the federated feature extension.
Learning Transferable Spatiotemporal Representations from Natural Script Knowledge
Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years.
Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection
In this paper, we revisit dataset ownership verification.
Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain
Specifically, MSFDPM consists of a side information feature extractor, a multi-scale feature domain patch matching module, and a multi-scale feature fusion network.
Imperceptible and Robust Backdoor Attack in 3D Point Cloud
Existing attacks often insert some additional points into the point cloud as the trigger, or utilize a linear transformation (e. g., rotation) to construct the poisoned point cloud.
Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution
Image representation is critical for many visual tasks.
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.
Black-box Dataset Ownership Verification via Backdoor Watermarking
The rapid development of DNNs has benefited from the existence of some high-quality datasets ($e. g.$, ImageNet), which allow researchers and developers to easily verify the performance of their methods.
Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications.
Versatile Weight Attack via Flipping Limited Bits
Utilizing the latest technique in integer programming, we equivalently reformulate this MIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method.
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
Specifically, our method exploits multi-modal knowledge of image-text pairs based on a vision and language pre-training (VLP) model.
Ranked #1 on
Multi-label zero-shot learning
on Open Images V4
VFed-SSD: Towards Practical Vertical Federated Advertising
As an emerging secure learning paradigm in lever-aging cross-agency private data, vertical federatedlearning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher.
A Comparative Study of Feature Expansion Unit for 3D Point Cloud Upsampling
Recently, deep learning methods have shown great success in 3D point cloud upsampling.
Improving Vision Transformers by Revisiting High-frequency Components
Inspired by this finding, we first investigate the effects of existing techniques for improving ViT models from a new frequency perspective, and find that the success of some techniques (e. g., RandAugment) can be attributed to the better usage of the high-frequency components.
Ranked #2 on
Domain Generalization
on Stylized-ImageNet
Adaptive Frequency Learning in Two-branch Face Forgery Detection
Face forgery has attracted increasing attention in recent applications of computer vision.
On the Effectiveness of Adversarial Training against Backdoor Attacks
To explore whether adversarial training could defend against backdoor attacks or not, we conduct extensive experiments across different threat models and perturbation budgets, and find the threat model in adversarial training matters.
Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels.
Few-Shot Backdoor Attacks on Visual Object Tracking
Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems.
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}.
Clustering Effect of Adversarial Robust Models
Adversarial robustness has received increasing attention along with the study of adversarial examples.
Clustering Effect of (Linearized) Adversarial Robust Models
Adversarial robustness has received increasing attention along with the study of adversarial examples.
Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment
For challenge B, we point out that the gradient contribution statistics can be a reliable indicator to inspect whether the optimization is dominated by bias-aligned samples.
Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association
This paper presents a new method to solve keypoint detection and instance association by using Transformer.
Ranked #10 on
Multi-Person Pose Estimation
on COCO
Does Adversarial Robustness Really Imply Backdoor Vulnerability?
Based on thorough experiments, we find that such trade-off ignores the interactions between the perturbation budget of adversarial training and the magnitude of the backdoor trigger.
Deep Dirichlet Process Mixture Models
In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning.
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
To this end, we propose the confusing perturbations-induced backdoor attack (CIBA).
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems.
Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
Deep hashing approaches, including deep quantization and deep binary hashing, have become a common solution to large-scale image retrieval due to high computation and storage efficiency.
SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
The 2D heatmap-based approaches have dominated Human Pose Estimation (HPE) for years due to high performance.
Universal Adversarial Head: Practical Protection against Video Data Leakage
We propose $universal \ adversarial \ head$ (UAH), which crafts adversarial query videos by prepending the original videos with a sequence of adversarial frames to perturb the normal hash codes in the Hamming space.
Learnable Hypergraph Laplacian for Hypergraph Learning
Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data.
Learnable Hypergraph Laplacian for Hypergraph Learning
HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.
Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
Deep quantization methods have shown high efficiency on large-scale image retrieval.
TokenPose: Learning Keypoint Tokens for Human Pose Estimation
Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints.
Backdoor Attack in the Physical World
We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.
Improving Adversarial Robustness via Channel-wise Activation Suppressing
The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs).
Hidden Backdoor Attack against Semantic Segmentation Models
Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data.
Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method.
Stochastic Deep Gaussian Processes over Graphs
In this paper we propose Stochastic Deep Gaussian Processes over Graphs (DGPG), which are deep structure models that learn the mappings between input and output signals in graph domains.
Backdoor Attack against Speaker Verification
We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.
JSRT: James-Stein Regression Tree
To address this issue, we propose a novel regression tree, named James-Stein Regression Tree (JSRT) by considering global information from different nodes.
DPAttack: Diffused Patch Attacks against Universal Object Detection
Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e. g.
Open-sourced Dataset Protection via Backdoor Watermarking
Based on the proposed backdoor-based watermarking, we use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model of the benign samples and their correspondingly watermarked samples ($i. e.$, images with trigger) on the target class.
Improving Query Efficiency of Black-box Adversarial Attack
Deep neural networks (DNNs) have demonstrated excellent performance on various tasks, however they are under the risk of adversarial examples that can be easily generated when the target model is accessible to an attacker (white-box setting).
Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning
Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality.
Neural Network-based Automatic Factor Construction
This paper proposes Neural Network-based Automatic Factor Construction (NNAFC), a tailored neural network framework that can automatically construct diversified financial factors based on financial domain knowledge and a variety of neural network structures.
Backdoor Learning: A Survey
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by attacker-specified triggers.
Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters
Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model.
Temporal Calibrated Regularization for Robust Noisy Label Learning
Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets.
Targeted Attack for Deep Hashing based Retrieval
In this paper, we propose a novel method, dubbed deep hashing targeted attack (DHTA), to study the targeted attack on such retrieval.
Adversarial Weight Perturbation Helps Robust Generalization
The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years.
Rethinking the Trigger of Backdoor Attack
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it performs well on benign samples.
Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels
Probabilistic modeling, which consists of a classifier and a transition matrix, depicts the transformation from true labels to noisy labels and is a promising approach.
Toward Adversarial Robustness via Semi-supervised Robust Training
In this work, we propose a novel defense method, the robust training (RT), by jointly minimizing two separated risks ($R_{stand}$ and $R_{rob}$), which is with respect to the benign example and its neighborhoods respectively.
Adversarial Attack on Deep Product Quantization Network for Image Retrieval
Deep product quantization network (DPQN) has recently received much attention in fast image retrieval tasks due to its efficiency of encoding high-dimensional visual features especially when dealing with large-scale datasets.
An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning
However, the strong defence ability and high learning accuracy of these schemes cannot be ensured at the same time, which will impede the wide application of FL in practice (especially for medical or financial institutions that require both high accuracy and strong privacy guarantee).
Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
We find that using more gradients from the skip connections rather than the residual modules according to a decay factor, allows one to craft adversarial examples with high transferability.
Alpha Discovery Neural Network based on Prior Knowledge
This paper proposes Alpha Discovery Neural Network (ADNN), a tailored neural network structure which can automatically construct diversified financial technical indicators based on prior knowledge.
Automatic Financial Feature Construction
According to neural network universal approximation theorem, pre-training can conduct a more effective and explainable evolution process.
Maintaining Discrimination and Fairness in Class Incremental Learning
In this paper, we demonstrate it can indeed help the model to output more discriminative results within old classes.
Ranked #2 on
Incremental Learning
on ImageNet100 - 10 steps
(# M Params metric)
Visual Privacy Protection via Mapping Distortion
To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios.
Deep Flow Collaborative Network for Online Visual Tracking
The deep learning-based visual tracking algorithms such as MDNet achieve high performance leveraging to the feature extraction ability of a deep neural network.
Adversarial Defense via Local Flatness Regularization
In this paper, we define the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discuss the relationship between the local flatness and adversarial vulnerability.
Training Interpretable Convolutional Neural Networks towards Class-specific Filters
Convolutional neural networks (CNNs) have often been treated as “black-box” and successfully used in a range of tasks.
AdaCompress: Adaptive Compression for Online Computer Vision Services
Then we train the agent in a reinforcement learning way to adapt it for different deep learning cloud services that act as the {\em interactive training environment} and feeding a reward with comprehensive consideration of accuracy and data size.
Multimedia Image and Video Processing
Adaptive Regularization of Labels
In addition, label regularization techniques such as label smoothing and label disturbance have also been proposed with the motivation of adding a stochastic perturbation to labels.
$t$-$k$-means: A Robust and Stable $k$-means Variant
$k$-means algorithm is one of the most classical clustering methods, which has been widely and successfully used in signal processing.
Self-Paced Probabilistic Principal Component Analysis for Data with Outliers
There is a probabilistic version of PCA, known as Probabilistic PCA (PPCA).
Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness
How to obtain a model with good interpretability and performance has always been an important research topic.
Multinomial Random Forest: Toward Consistency and Privacy-Preservation
Despite the impressive performance of random forests (RF), its theoretical properties have not been thoroughly understood.
BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training
In distributed machine learning (DML), the network performance between machines significantly impacts the speed of iterative training.
Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization
Learning vector space representation of words (i. e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario.
Dimensionality-Driven Learning with Noisy Labels
Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs).
Ranked #39 on
Image Classification
on mini WebVision 1.0
Iterative Learning with Open-set Noisy Labels
We refer to this more complex scenario as the \textbf{open-set noisy label} problem and show that it is nontrivial in order to make accurate predictions.
Nonextensive information theoretical machine
In this paper, we propose a new discriminative model named \emph{nonextensive information theoretical machine (NITM)} based on nonextensive generalization of Shannon information theory.
Bayesian linear regression with Student-t assumptions
In this paper, we propose a Bayesian linear regression model with Student-t assumptions (BLRS), which can be inferred exactly.
Unifying Decision Trees Split Criteria Using Tsallis Entropy
In this paper, a Tsallis Entropy Criterion (TEC) algorithm is proposed to unify Shannon entropy, Gain Ratio and Gini index, which generalizes the split criteria of decision trees.
