MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4514-4524
Abstract
Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve reasonable improvements in performance, they typically perform category-agnostic domain alignment, thereby resulting in negative transfer of features. To overcome this issue, in this work, we attempt to incorporate category information into the domain adaptation process by proposing Memory Guided Attention for Category-Aware Domain Adaptation (MeGA-CDA). The proposed method consists of employing category-wise discriminators to ensure category-aware feature alignment for learning domain-invariant discriminative features. However, since the category information is not available for the target samples, we propose to generate memory-guided category-specific attention maps which are then used to route the features appropriately to the corresponding category discriminator. The proposed method is evaluated on several benchmark datasets and is shown to outperform existing approaches.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Adversarial Discriminative Domain Adaptation2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Domain Adaptive Subspace Clustering2016
- Visual Domain Adaptation: A survey of recent advancesIEEE Signal Processing Magazine, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- A theory of learning from different domainsMachine Learning, 2009
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Rapid object detection using a boosted cascade of simple features2005