Devavrat Tomar — accepted AI-conference papers

2025

ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains

Guillaume Vray, Devavrat Tomar, Xufeng Gao, Jean-Philippe Thiran, Evan Shelhamer, Behzad Bozorgtabar

NeurIPS 2025poster

This paper introduces **ReservoirTTA**, a novel plug–in framework designed for prolonged test–time adaptation (TTA) in scenarios where the test domain continuously shifts over time, including cases where domains recur or evolve gradually. At its core, ReservoirTTA maintains a reservoir of domain-spe…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation

Devavrat Tomar, Guillaume Vray, Jean-Philippe Thiran, Behzad Bozorgtabar

ICLR 2024poster

Recent test-time adaptation methods heavily rely on nuanced adjustments of batch normalization (BN) parameters. However, one critical assumption often goes overlooked: that of independently and identically distributed (i.i.d.) test batches with respect to unknown labels. This oversight leads to ske…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2023

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Devavrat Tomar, Guillaume Vray, Behzad Bozorgtabar, Jean-Philippe Thiran

CVPR 2023poster

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Test-time Self-Learning method with automatic A…

Cited by 37 Source ↗PDF ↗code ↗Scholar ↗