Saved in:
Bibliographic Details
Main Authors: Ashraf, Tajamul, Manna, Rajes, Purkayastha, Partha Sarathi, Tariq, Tavaheed, Bashir, Janibul
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.15404
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911711716442112
author Ashraf, Tajamul
Manna, Rajes
Purkayastha, Partha Sarathi
Tariq, Tavaheed
Bashir, Janibul
author_facet Ashraf, Tajamul
Manna, Rajes
Purkayastha, Partha Sarathi
Tariq, Tavaheed
Bashir, Janibul
contents Source-free object detection (SFOD) faces persistent challenges due to class imbalance-driven context bias and instability in teacher-student training under noisy pseudo-labels. Existing techniques tend to ignore context bias and class-imbalance shifts, especially in medical data. To tackle this, we propose Grounded Teacher (GT), a bias-aware source-free framework that grounds the teacher model through relational and semantic regularization. To explicitly model directional confusion between classes, GT introduces a Relational Context Module (RCM) that maintains an exponential moving average (EMA) estimate of cross-domain contextual bias. Building upon this, a Semantic Augmentation (SA) strategy selectively augments minority and confusable classes through adaptive MixUp in both source-similar and source-dissimilar target regions, improving minority recall without overfitting dominant categories. To stabilize learning under biased pseudo-labels, we design a Semantic-Aware Loss (SAL) that applies diagonally normalized weights, preventing gradient explosion while emphasizing minority-majority corrections. Additionally, a frozen Expert branch derived from large vision foundation models (LVFMs) serves as a supervisory reference during training, refining pseudo-label quality without adding inference overhead. GT's behavior-driven bias quantification makes it broadly applicable across domains without relying on dataset priors. Evaluations on Cityscapes-to-Foggy (50.8 mAP) and medical transfers (+5.9 AP50 on DDSM-to-INBreast) show consistent gains and improved minority-class detection, with less than 12\% additional training cost. Code and model are available at https://github.com/Tajamul21/Grounded-Teacher.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15404
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context Aware Grounded Teacher for Source Free Object Detection
Ashraf, Tajamul
Manna, Rajes
Purkayastha, Partha Sarathi
Tariq, Tavaheed
Bashir, Janibul
Computer Vision and Pattern Recognition
Source-free object detection (SFOD) faces persistent challenges due to class imbalance-driven context bias and instability in teacher-student training under noisy pseudo-labels. Existing techniques tend to ignore context bias and class-imbalance shifts, especially in medical data. To tackle this, we propose Grounded Teacher (GT), a bias-aware source-free framework that grounds the teacher model through relational and semantic regularization. To explicitly model directional confusion between classes, GT introduces a Relational Context Module (RCM) that maintains an exponential moving average (EMA) estimate of cross-domain contextual bias. Building upon this, a Semantic Augmentation (SA) strategy selectively augments minority and confusable classes through adaptive MixUp in both source-similar and source-dissimilar target regions, improving minority recall without overfitting dominant categories. To stabilize learning under biased pseudo-labels, we design a Semantic-Aware Loss (SAL) that applies diagonally normalized weights, preventing gradient explosion while emphasizing minority-majority corrections. Additionally, a frozen Expert branch derived from large vision foundation models (LVFMs) serves as a supervisory reference during training, refining pseudo-label quality without adding inference overhead. GT's behavior-driven bias quantification makes it broadly applicable across domains without relying on dataset priors. Evaluations on Cityscapes-to-Foggy (50.8 mAP) and medical transfers (+5.9 AP50 on DDSM-to-INBreast) show consistent gains and improved minority-class detection, with less than 12\% additional training cost. Code and model are available at https://github.com/Tajamul21/Grounded-Teacher.
title Context Aware Grounded Teacher for Source Free Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.15404