iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection
arXiv:2003.04132
Abstract
Training an object detector on a data-rich domain and applying it to a data-poor one with limited performance drop is highly attractive in industry, because it saves huge annotation cost. Recent research on unsupervised domain adaptive object detection has verified that aligning data distributions between source and target images through adversarial learning is very useful. The key is when, where and how to use it to achieve best practice. We propose Image-Instance Full Alignment Networks (iFAN) to tackle this problem by precisely aligning feature distributions on both image and instance levels: 1) Image-level alignment: multi-scale features are roughly aligned by training adversarial domain classifiers in a hierarchically-nested fashion. 2) Full instance-level alignment: deep semantic information and elaborate instance representations are fully exploited to establish a strong relationship among categories and domains. Establishing these correlations is formulated as a metric learning problem by carefully constructing instance pairs. Above-mentioned adaptations can be integrated into an object detector (e.g. Faster RCNN), resulting in an end-to-end trainable framework where multiple alignments can work collaboratively in a coarse-tofine manner. In two domain adaptation tasks: synthetic-to-real (SIM10K->Cityscapes) and normal-to-foggy weather (Cityscapes->Foggy Cityscapes), iFAN outperforms the state-of-the-art methods with a boost of 10%+ AP over the source-only baseline.
arXiv commentAAAI 2020
References in corpus (11)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Conditional Adversarial Domain Adaptation
- Semantic Foggy Scene Understanding with Synthetic Data
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- A DIRT-T Approach to Unsupervised Domain Adaptation
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- Co-regularized Alignment for Unsupervised Domain Adaptation
- Few-shot Adaptive Faster R-CNN
- Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving
- Learning Continuous Face Age Progression: A Pyramid of GANs