Instance-Invariant Adaptive Object Detection via Progressive Disentanglement

by   Aming Wu, et al.

Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains, e.g., with different styles. To address this problem, previous methods mainly use holistic representations to align feature-level and pixel-level distributions of different domains, which may neglect the instance-level characteristics of objects in images. Besides, when transferring detection ability across different domains, it is important to obtain the instance-level features that are domain-invariant, instead of the styles that are domain-specific. Therefore, in order to extract instance-invariant features, we should disentangle the domain-invariant features from the domain-specific features. To this end, a progressive disentangled framework is first proposed to solve domain adaptive object detection. Particularly, base on disentangled learning used for feature decomposition, we devise two disentangled layers to decompose domain-invariant and domain-specific features. And the instance-invariant features are extracted based on the domain-invariant features. Finally, to enhance the disentanglement, a three-stage training mechanism including multiple loss functions is devised to optimize our model. In the experiment, we verify the effectiveness of our method on three domain-shift scenes. Our method is separately 2.3%, 3.6%, and 4.0% higher than the baseline method <cit.>.


page 1

page 7

page 8

page 10


Vector-Decomposed Disentanglement for Domain-Invariant Object Detection

To improve the generalization of detectors, for domain adaptive object d...

Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection

Domain adaptive object detection (DAOD) aims to improve the generalizati...

Gated Domain-Invariant Feature Disentanglement for Domain Generalizable Object Detection

For Domain Generalizable Object Detection (DGOD), Disentangled Represent...

Domain-Invariant Proposals based on a Balanced Domain Classifier for Object Detection

Object recognition from images means to automatically find object(s) of ...

Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection

Domain adaptation for object detection (DAOD) has recently drawn much at...

Adapting Object Detectors with Conditional Domain Normalization

Real-world object detectors are often challenged by the domain gaps betw...

Please sign up or login with your details

Forgot password? Click here to reset