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

06/10/2021
by   Hongsong Wang, et al.
0

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend to suffer from a shortage of annotated training samples. Moreover, existing methods of feature alignments are not sufficient to learn domain-invariant representations. To address these limitations, we propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training into a unified framework. An intermediate domain image generator is proposed to enhance feature alignments by domain-adversarial training with automatically generated soft domain labels. The synthetic intermediate domain images progressively bridge the domain divergence and augment the annotated source domain training data. A feature pyramid alignment is designed and the corresponding feature discriminator is used to align multi-scale convolutional features of different semantic levels. Last but not least, we introduce a region feature alignment and an instance discriminator to learn domain-invariant features for object proposals. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations. Further extensive experiments verify the effectiveness of each component and demonstrate that the proposed network can learn domain-invariant representations.

READ FULL TEXT

page 1

page 8

page 9

research
03/27/2023

AIR-DA: Adversarial Image Reconstruction for Unsupervised Domain Adaptive Object Detection

Unsupervised domain adaptive object detection is a challenging vision ta...
research
11/14/2020

Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

Recently the problem of cross-domain object detection has started drawin...
research
02/03/2020

Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation

We present a novel approach to perform the unsupervised domain adaptatio...
research
03/22/2021

Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation

Many unsupervised domain adaptation (UDA) methods exploit domain adversa...
research
03/31/2022

Multi-Granularity Alignment Domain Adaptation for Object Detection

Domain adaptive object detection is challenging due to distinctive data ...
research
03/09/2020

iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection

Training an object detector on a data-rich domain and applying it to a d...
research
07/24/2019

Multi-adversarial Faster-RCNN for Unrestricted Object Detection

Conventional object detection methods essentially suppose that the train...

Please sign up or login with your details

Forgot password? Click here to reset