Progressive Domain Adaptation for Object Detection
Autor: | Maneesh Singh, Wei-Chih Hung, Yi-Hsuan Tsai, Han-Kai Hsu, Ming-Hsuan Yang, Hung-Yu Tseng, Chun-Han Yao |
---|---|
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer science Image quality business.industry Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition 02 engineering and technology 010501 environmental sciences 01 natural sciences Object detection Task (project management) Domain (software engineering) Feature (computer vision) Minimum bounding box 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Adaptation (computer science) 0105 earth and related environmental sciences |
Zdroj: | WACV |
DOI: | 10.48550/arxiv.1910.11319 |
Popis: | Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different distribution. Domain adaptation provides a solution by adapting existing labels to the target testing data. However, a large gap between domains could make adaptation a challenging task, which leads to unstable training processes and sub-optimal results. In this paper, we propose to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks. This intermediate domain is constructed by translating the source images to mimic the ones in the target domain. To tackle the domain-shift problem, we adopt adversarial learning to align distributions at the feature level. In addition, a weighted task loss is applied to deal with unbalanced image quality in the intermediate domain. Experimental results show that our method performs favorably against the state-of-the-art method in terms of the performance on the target domain. Comment: Accepted in WACV'20. Code and models will be available at https://github.com/kevinhkhsu/DA_detection |
Databáze: | OpenAIRE |
Externí odkaz: |