Task-specific Inconsistency Alignment for Domain Adaptive Object Detection

03/29/2022
by   Liang Zhao, et al.
7

Detectors trained with massive labeled data often exhibit dramatic performance degradation in some particular scenarios with data distribution gap. To alleviate this problem of domain shift, conventional wisdom typically concentrates solely on reducing the discrepancy between the source and target domains via attached domain classifiers, yet ignoring the difficulty of such transferable features in coping with both classification and localization subtasks in object detection. To address this issue, in this paper, we propose Task-specific Inconsistency Alignment (TIA), by developing a new alignment mechanism in separate task spaces, improving the performance of the detector on both subtasks. Specifically, we add a set of auxiliary predictors for both classification and localization branches, and exploit their behavioral inconsistencies as finer-grained domain-specific measures. Then, we devise task-specific losses to align such cross-domain disagreement of both subtasks. By optimizing them individually, we are able to well approximate the category- and boundary-wise discrepancies in each task space, and therefore narrow them in a decoupled manner. TIA demonstrates superior results on various scenarios to the previous state-of-the-art methods. It is also observed that both the classification and localization capabilities of the detector are sufficiently strengthened, further demonstrating the effectiveness of our TIA method. Code and trained models are publicly available at https://github.com/MCG-NJU/TIA.

READ FULL TEXT

page 1

page 3

page 13

page 14

research
09/17/2020

Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection

Object detectors are usually trained with large amount of labeled data, ...
research
03/28/2020

Cross-domain Detection via Graph-induced Prototype Alignment

Applying the knowledge of an object detector trained on a specific domai...
research
05/03/2022

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

Cross domain object detection is a realistic and challenging task in the...
research
08/17/2021

TOOD: Task-aligned One-stage Object Detection

One-stage object detection is commonly implemented by optimizing two sub...
research
08/16/2023

GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds

LiDAR-based 3D detection has made great progress in recent years. Howeve...
research
11/29/2022

AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning

Recent studies have shown the impressive efficacy of counterfactually au...
research
09/27/2022

A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields

In this paper we evaluate the impact of domain shift on human detection ...

Please sign up or login with your details

Forgot password? Click here to reset