상세정보
학술지
Exploiting domain transferability for collaborative inter-level domain adaptive object detection
- 저자
- 도미래, 전석규, 이필현, 홍기범, 마유승, 변혜란
- 발행일
- 202211
- 출처
- Expert Systems with Applications, v.205, pp.1-12
- ISSN
- 0957-4174
- 출판사
- Elsevier
- 협약과제
- 22HS2300, 인공지능 시스템을 위한 뉴로모픽 컴퓨팅 SW 플랫폼 기술 개발, 김태호
- 초록
- Domain adaptation for object detection (DAOD) has recently drawn much attention owing to its capability of detecting target objects without any annotations. To tackle the problem, previous works focus on aligning features extracted from partial levels (e.g., image-level, instance-level, RPN-level) in a two-stage detector via adversarial training. However, individual levels in the object detection pipeline are closely related to each other and this inter-level relation is unconsidered yet. To this end, we introduce a novel framework for DAOD with three proposed components: Multi-scale-aware Uncertainty Attention (MUA), Transferable Region Proposal Network (TRPN), and Dynamic Instance Sampling (DIS). With these modules, we seek to reduce the negative transfer effect during training while maximizing transferability as well as discriminability in both domains. Finally, our framework implicitly learns domain invariant regions for object detection via exploiting the transferable information and enhances the complementarity between different detection levels by collaboratively utilizing their domain information. Through ablation studies and experiments, we show that the proposed modules contribute to the performance improvement in a synergic way, demonstrating the effectiveness of our method. Moreover, our model achieves a new state-of-the-art performance on various benchmarks.
- KSP 제안 키워드
- Adaptive Object, Adversarial Training, Art performance, Domain information, Multi-scale, Negative transfer, Object detection, Region Proposal Network, Transfer effect, Two-Stage, detection domain