6 citations · 11 across the 6 of their papers we have counts for
6 papers
BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder
Siquan Huang, Yijiang Li, Ningzhi Gao +3
Self-supervised and multimodal vision encoders learn strong visual representations that are widely adopted in downstream vision tasks and large vision-language models (LVLMs). Howe…
Towards Understanding Adversarial Transferability in Federated Learning
Yijiang Li, Ying Gao, Haohan Wang
We investigate a specific security risk in FL: a group of malicious clients has impacted the model during training by disguising their identities and acting as benign clients but l…
Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Yijiang Li, Xinjiang Wang, Lihe Yang +3
Deep co-training has been introduced to semi-supervised segmentation and achieves impressive results, yet few studies have explored the working mechanism behind it. In this work, w…
Multi-metrics adaptively identifies backdoors in Federated learning
Siquan Huang, Yijiang Li, Chong Chen +2
The decentralized and privacy-preserving nature of federated learning (FL) makes it vulnerable to backdoor attacks aiming to manipulate the behavior of the resulting model on speci…
Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
Xinjiang Wang, Xingyi Yang, Shilong Zhang +6
In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD). Our core observation is that the oscillating pseudo-targets undermi…
More than Encoder: Introducing Transformer Decoder to Upsample
Yijiang Li, Wentian Cai, Ying Gao +2
Medical image segmentation methods downsample images for feature extraction and then upsample them to restore resolution for pixel-level predictions. In such a schema, upsample tec…