MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection

by   Vibashan VS, et al.

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.


page 3

page 8

page 13

page 14


Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) aims to enhance the generalization ...

Discriminative Adversarial Domain Adaptation

Given labeled instances on a source domain and unlabeled ones on a targe...

Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box

Most existing domain adaptive object detection methods exploit adversari...

CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

Unsupervised domain adaptation without consuming annotation process for ...

Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment

Detection transformers like DETR have recently shown promising performan...

Universal Domain Adaptive Object Detector

Universal domain adaptive object detection (UniDAOD)is more challenging ...

AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection

Unsupervised domain adaptation for object detection is a challenging pro...