29 citations · 116 across the 20 of their papers we have counts for
20 papers
Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach
Taolin Zhang, Jiawang Bai, Zhihe Lu +4
Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable…
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
Sheng Yang, Jiawang Bai, Kuofeng Gao +3
Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tas…
Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
Kuofeng Gao, Yang Bai, Jiawang Bai +2
Multi-modal Large Language Models (MLLMs) have recently achieved enhanced performance across various vision-language tasks including visual grounding capabilities. However, the adv…
Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models
Zhihe Lu, Jiawang Bai, Xin Li +2
Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performan…
BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
Jiawang Bai, Kuofeng Gao, Shaobo Min +3
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the…
GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
Xin Li, Dongze Lian, Zhihe Lu +3
Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additiona…
A Dive into SAM Prior in Image Restoration
Zeyu Xiao, Jiawang Bai, Zhihe Lu +1
The goal of image restoration (IR), a fundamental issue in computer vision, is to restore a high-quality (HQ) image from its degraded low-quality (LQ) observation. Multiple HQ solu…
Can SAM Boost Video Super-Resolution?
Zhihe Lu, Zeyu Xiao, Jiawang Bai +2
The primary challenge in video super-resolution (VSR) is to handle large motions in the input frames, which makes it difficult to accurately aggregate information from multiple fra…
Reliable and Efficient Evaluation of Adversarial Robustness for Deep Hashing-Based Retrieval
Xunguang Wang, Jiawang Bai, Xinyue Xu +1
Deep hashing has been extensively applied to massive image retrieval due to its efficiency and effectiveness. Recently, several adversarial attacks have been presented to reveal th…
Imperceptible and Robust Backdoor Attack in 3D Point Cloud
Kuofeng Gao, Jiawang Bai, Baoyuan Wu +2
With the thriving of deep learning in processing point cloud data, recent works show that backdoor attacks pose a severe security threat to 3D vision applications. The attacker inj…
Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
Jiawang Bai, Kuofeng Gao, Dihong Gong +3
The security of deep neural networks (DNNs) has attracted increasing attention due to their widespread use in various applications. Recently, the deployed DNNs have been demonstrat…
Versatile Weight Attack via Flipping Limited Bits
Jiawang Bai, Baoyuan Wu, Zhifeng Li +1
To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the…
Improving Vision Transformers by Revisiting High-frequency Components
Jiawang Bai, Li Yuan, Shu-Tao Xia +3
The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training…
Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
Kuofeng Gao, Jiawang Bai, Bin Chen +2
A backdoored deep hashing model is expected to behave normally on original query images and return the images with the target label when a specific trigger pattern presents. To thi…
Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
Jiawang Bai, Baoyuan Wu, Yong Zhang +3
To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the…
Open-sourced Dataset Protection via Backdoor Watermarking
Yiming Li, Ziqi Zhang, Jiawang Bai +3
The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets (, ImageNet), which allows researchers to easily verify the e…
Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning
Yiming Li, Jiawang Bai, Jiawei Li +3
Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality. In this paper, we propose a knowledge distilla…
Targeted Attack for Deep Hashing based Retrieval
Jiawang Bai, Bin Chen, Yiming Li +4
The deep hashing based retrieval method is widely adopted in large-scale image and video retrieval. However, there is little investigation on its security. In this paper, we propos…
Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness
Jiawang Bai, Yiming Li, Jiawei Li +2
How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge…
Multinomial Random Forest: Toward Consistency and Privacy-Preservation
Yiming Li, Jiawang Bai, Jiawei Li +4
Despite the impressive performance of random forests (RF), its theoretical properties have not been thoroughly understood. In this paper, we propose a novel RF framework, dubbed mu…