Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptive Object Detection
Belal, Atif, Meethal, Akhil, Romero, Francisco Perdigon, Pedersoli, Marco, Granger, Eric
–arXiv.org Artificial Intelligence
Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets, and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modal information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation due to noisy pseudo-labels which can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment scheme for MSDA that aligns instances of each object category across domains. In particular, an attention module coupled with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms the state-of-the-art methods and is robust to class imbalance. Our code is available at https://github.com/imatif17/ACIA.
arXiv.org Artificial Intelligence
Mar-14-2024
- Country:
- Europe > Portugal (0.14)
- North America > Canada (0.14)
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (0.46)
- Natural Language (1.00)
- Vision (1.00)
- Information Technology > Artificial Intelligence