CycDA: Unsupervised Cycle Domain Adaptation from Image to Video
Preprint
Abstract
Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Therefore, image-to-video adaptation has been proposed to exploit labeling-free web image source for adapting on unlabeled target videos. This poses two major challenges: (1) spatial domain shift between web images and video frames; (2) modality gap between image and video data. To address these challenges, we propose Cycle Domain Adaptation (CycDA), a cycle-based approach for unsupervised image-to-video domain adaptation by leveraging the joint spatial information in images and videos on the one hand and, on the other hand, training an independent spatio-temporal model to bridge the modality gap. We alternate between the spatial and spatio-temporal learning with knowledge transfer between the two in each cycle. We evaluate our approach on benchmark datasets for image-to-video as well as for mixed-source domain adaptation achieving state-of-the-art results and demonstrating the benefits of our cyclic adaptation.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Label Propagation with Augmented Anchors: A Simple Semi-supervised Learning Baseline for Unsupervised Domain Adaptation2020
- Shuffle and Attend: Video Domain Adaptation2020
- Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training2018
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images2018
- Adaptive Batch Normalization for practical domain adaptationPattern Recognition, 2018
- Do less and achieve more: Training CNNs for action recognition utilizing action images from the WebPattern Recognition, 2017
- Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames2016
- Deep Residual Learning for Image Recognition2016
- You Lead, We Exceed: Labor-Free Video Concept Learning by Jointly Exploiting Web Videos and Images2016
- Facial descriptors for human interaction recognition in still imagesPattern Recognition Letters, 2016