23 citations · 71 across the 20 of their papers we have counts for
11 papers · 1 filter
Boundary Matters: A Bi-Level Active Finetuning Framework
Han Lu, Yichen Xie, Xiaokang Yang +1
The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To miti…
ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
Han Lu, Xiaosong Jia, Yichen Xie +3
End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled…
Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach
Han Lu, Siyu Sun, Yichen Xie +3
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods. This paradigm decouples the training process i…
SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction
Zelin Peng, Zhengqin Xu, Zhilin Zeng +2
Segment Anything Model (SAM) has received remarkable attention as it offers a powerful and versatile solution for object segmentation in images. However, fine-tuning SAM for downst…
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
Yichen Xie, Han Lu, Junchi Yan +3
Given the large-scale data and the high annotation cost, pretraining-finetuning becomes a popular paradigm in multiple computer vision tasks. Previous research has covered both the…
Xformer: Hybrid X-Shaped Transformer for Image Denoising
Jiale Zhang, Yulun Zhang, Jinjin Gu +3
In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation o…
Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
Shuai Jia, Bangjie Yin, Taiping Yao +4
Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels,…
A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Wei Shen, Zelin Peng, Xuehui Wang +6
The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithm…
Continual Predictive Learning from Videos
Geng Chen, Wendong Zhang, Han Lu +4
Predictive learning ideally builds the world model of physical processes in one or more given environments. Typical setups assume that we can collect data from all environments at…
Exploring Frequency Adversarial Attacks for Face Forgery Detection
Shuai Jia, Chao Ma, Taiping Yao +3
Various facial manipulation techniques have drawn serious public concerns in morality, security, and privacy. Although existing face forgery classifiers achieve promising performan…
EAutoDet: Efficient Architecture Search for Object Detection
Xiaoxing Wang, Jiale Lin, Junchi Yan +2
Training CNN for detection is time-consuming due to the large dataset and complex network modules, making it hard to search architectures on detection datasets directly, which usua…