Strong-Weak Distribution Alignment for Adaptive Object Detection

12/12/2018
by   Kuniaki Saito, et al.
48

We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source and target images using an adversarial loss have been proven effective for adapting object classifiers. However, for object detection, fully matching the entire distributions of source and target images to each other at the global image level may fail, as domains could have distinct scene layouts and different combinations of objects. On the other hand, strong matching of local features such as texture and color makes sense, as it does not change category level semantics. This motivates us to propose a novel approach for detector adaptation based on strong local alignment and weak global alignment. Our key contribution is the weak alignment model, which focuses the adversarial alignment loss on images that are globally similar and puts less emphasis on aligning images that are globally dissimilar. Additionally, we design the strong domain alignment model to only look at local receptive fields of the feature map. We empirically verify the effectiveness of our approach on several detection datasets comprising both large and small domain shifts.

READ FULL TEXT

page 1

page 4

page 8

page 14

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
03/09/2020

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
10/04/2021

Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection

In order to robustly deploy object detectors across a wide range of scen...
research
03/13/2020

Harmonizing Transferability and Discriminability for Adapting Object Detectors

Recent advances in adaptive object detection have achieved compelling re...
research
01/01/2023

Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment

Domain adaptive detection aims to improve the generalization of detector...
research
04/14/2023

DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection

This paper presents a DETR-based method for cross-domain weakly supervis...
research
04/27/2013

Bingham Procrustean Alignment for Object Detection in Clutter

A new system for object detection in cluttered RGB-D images is presented...

Please sign up or login with your details

Forgot password? Click here to reset