Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection
| العنوان: | Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection |
|---|---|
| المؤلفون: | Tiejun Huang, Peixi Peng, Zongxian Li, Yonghong Tian, Shijian Lu, Chong Zhang, Jingjing Liu, Qixiang Ye |
| المصدر: | IEEE Transactions on Multimedia. 24:2246-2258 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Computer science, business.industry, Sampling (statistics), Pattern recognition, Sample (statistics), Object detection, Computer Science Applications, Domain (software engineering), Kernel (image processing), Feature (computer vision), Robustness (computer science), Signal Processing, Media Technology, Artificial intelligence, Electrical and Electronic Engineering, Representation (mathematics), business |
| الوصف: | Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. However, existing UDA methods largely ignore the instantaneous data distribution and the sampling strategy during model learning, which could deteriorate the feature representation given large domain shift. In this work, we propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains while considering the instantaneous alignment difficulty. The core of SGA is to calculate "hardness" factors for sample pairs indicating domain distance in a kernel space. With the hardness factor, the proposed SGA adaptively indicates the importance of samples and assigns them different constrains. Indicated by hardness factors, Self-Guided Progressive Sampling (SPS) is implemented in an "easy-to-hard" way during model adaptation. Using multi-stage convolutional features, SGA is further aggregated to fully align hierarchical representations of detection models. Extensive experiments on commonly used benchmarks show that SGA improves the state-of-the-art methods with significant margins, while demonstrating the effectiveness on large domain shift. |
| تدمد: | 1941-0077 1520-9210 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::1d9815c7486440008166c8797864bc82 https://doi.org/10.1109/tmm.2021.3078141 |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi...........1d9815c7486440008166c8797864bc82 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 19410077 15209210 |
|---|