top of page

News to help your R&D in artificial intelligence, machine learning, robotics, computer vision, smart hardware

As an Amazon Associate I earn

from qualifying purchases

Writer's picturemorrislee

Detect objects in new domain by distilling more balanced source features with DUA-DA

Detect objects in new domain by distilling more balanced source features with DUA-DA


DUA-DA: Distillation-based Unbiased Alignment for Domain Adaptive Object Detection

arXiv paper abstract https://arxiv.org/abs/2311.10437



... Adaptive Object Detection (DAOD) have ... source bias issue, i.e. the aligned features are more favorable towards the source domain, leading to a sub-optimal adaptation.


... domain shift between the source and target domains exacerbates the problem of inconsistent classification and localization in general detection pipelines.


... propose a novel Distillation-based Unbiased Alignment (DUA) framework for DAOD, which can distill the source features towards a more balanced position via a pre-trained teacher model during the training process, alleviating the problem of source bias effectively.


... design a Target-Relevant Object Localization Network (TROLN), which can mine target-related knowledge to produce two classification-free metrics (IoU and centerness).


... implement a Domain-aware Consistency Enhancing (DCE) strategy that utilizes these two metrics to further refine classification confidences, achieving a harmonization between classification and localization in cross-domain scenarios.


... this method ... consistently improves the strong baseline by large margins, outperforming existing alignment-based works.



Please like and share this post if you enjoyed it using the buttons at the bottom!


Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact

Web site with my other posts by category https://morrislee1234.wixsite.com/website



14 views0 comments

Commentaires


ClickBank paid link

bottom of page