activity
20242026
collaborators

8 papers

cs.CV2026

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang +6

Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data…

cs.CV2026

Learnability-Driven Submodular Optimization for Active Roadside 3D Detection

Ruiyu Mao, Baoming Zhang, Nicholas Ruozzi +1

Roadside perception datasets are typically constructed via cooperative labeling between synchronized vehicle and roadside frame pairs. However, real deployment often requires annot…

cs.CV2025

SafeFix: Targeted Model Repair via Controlled Image Generation

Ouyang Xu, Baoming Zhang, Ruiyu Mao +1

Deep learning models for visual recognition often exhibit systematic errors due to underrepresented semantic subpopulations. Although existing debugging frameworks can pinpoint the…

cs.CV2025

: Bimodal Online Test-Time Adaptation for CLIP

Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky +2

Although open-vocabulary classification models like Contrastive Language Image Pretraining (CLIP) have demonstrated strong zero-shot learning capabilities, their robustness to comm…

cs.RO2025

SELECT: A Submodular Approach for Active LiDAR Semantic Segmentation

Ruiyu Mao, Sarthak Kumar Maharana, Xulong Tang +1

LiDAR-based semantic segmentation plays a vital role in autonomous driving by enabling detailed understanding of 3D environments. However, annotating LiDAR point clouds is extremel…

cs.CV2025

PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation

Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test…