Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing

About

Unsupervised Domain Adaptation (UDA) for object detection aims to adapt a model trained on a source domain to detect instances from a new target domain for which annotations are not available. Different from traditional approaches, we propose ConfMix, the first method that introduces a sample mixing strategy based on region-level detection confidence for adaptive object detector learning. We mix the local region of the target sample that corresponds to the most confident pseudo detections with a source image, and apply an additional consistency loss term to gradually adapt towards the target data distribution. In order to robustly define a confidence score for a region, we exploit the confidence score per pseudo detection that accounts for both the detector-dependent confidence and the bounding box uncertainty. Moreover, we propose a novel pseudo labelling scheme that progressively filters the pseudo target detections using the confidence metric that varies from a loose to strict manner along the training. We perform extensive experiments with three datasets, achieving state-of-the-art performance in two of them and approaching the supervised target model performance in the other. Code is available at: https://github.com/giuliomattolin/ConfMix.

Giulio Mattolin, Luca Zanella, Elisa Ricci, Yiming Wang• 2022

Related benchmarks

TaskDatasetResultRank
Object DetectionCityscapes to Foggy Cityscapes severity 0.02 1.0 (val)
AP (Person)45
22
Object DetectionINBreast (adapted from DDSM) (test)
Recall @0.050.19
14
Object DetectionINBreast (test)
AP (car)56.3
11
Breast cancer detectionDDSM to INBreast (test)
Recall @ 0.0519
11
Abnormality DetectionIn-house to DDSM
R@0.052
11
Breast cancer detectionIn-house to RSNA-BSD1K (test)
Recall @ FPR=0.0518
11
Breast cancer detectionDDSM to In-house (test)
Recall @ FPR=0.059
11
Abnormality DetectionRSNA-BSD1K to In-house
R@0.053
11
Breast cancer detectionIn-house to INBreast (test)
Recall @ FPR=0.053
11
Showing 9 of 9 rows

Other info

Follow for update