Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation

by   Xiyu Wang, et al.

Continuous Video Domain Adaptation (CVDA) is a scenario where a source model is required to adapt to a series of individually available changing target domains continuously without source data or target supervision. It has wide applications, such as robotic vision and autonomous driving. The main underlying challenge of CVDA is to learn helpful information only from the unsupervised target data while avoiding forgetting previously learned knowledge catastrophically, which is out of the capability of previous Video-based Unsupervised Domain Adaptation methods. Therefore, we propose a Confidence-Attentive network with geneRalization enhanced self-knowledge disTillation (CART) to address the challenge in CVDA. Firstly, to learn from unsupervised domains, we propose to learn from pseudo labels. However, in continuous adaptation, prediction errors can accumulate rapidly in pseudo labels, and CART effectively tackles this problem with two key modules. Specifically, The first module generates refined pseudo labels using model predictions and deploys a novel attentive learning strategy. The second module compares the outputs of augmented data from the current model to the outputs of weakly augmented data from the source model, forming a novel consistency regularization on the model to alleviate the accumulation of prediction errors. Extensive experiments suggest that the CVDA performance of CART outperforms existing methods by a considerable margin.


page 8

page 11


Black-box Source-free Domain Adaptation via Two-stage Knowledge Distillation

Source-free domain adaptation aims to adapt deep neural networks using o...

Confidence Regularized Self-Training

Recent advances in domain adaptation show that deep self-training presen...

From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation

Animal pose estimation is an important field that has received increasin...

Transformer-Based Source-Free Domain Adaptation

In this paper, we study the task of source-free domain adaptation (SFDA)...

Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision

Unsupervised Domain Adaptation (UDA) has attracted a surge of interest o...

Consistency Regularization for Generalizable Source-free Domain Adaptation

Source-free domain adaptation (SFDA) aims to adapt a well-trained source...

Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation

Deep regression trackers are among the fastest tracking algorithms avail...

Please sign up or login with your details

Forgot password? Click here to reset