4 papers · 1 filter
Generalizable Federated Learning using Client Adaptive Focal Modulation
Tajamul Ashraf, Iqra Altaf Gillani
Federated learning (FL) has proven essential for privacy-preserving, collaborative training across distributed clients. Our prior work, TransFed, introduced a robust transformer-ba…
TITAN: Query-Token based Domain Adaptive Adversarial Learning
Tajamul Ashraf, Janibul Bashir
We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target dom…
ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning
Tajamul Ashraf, Mohammed Mohsen Peerzada, Moloud Abdar +5
Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralized participants. As FL adoption grows,…
Context Aware Grounded Teacher for Source Free Object Detection
Tajamul Ashraf, Rajes Manna, Partha Sarathi Purkayastha +2
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. Ex…