1 citations · 1 across the 10 of their papers we have counts for
10 papers
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…
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…
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…
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…
: 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…
GradAlign for Training-free Model Performance Inference
Yuxuan Li, Yunhui Guo
Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search spac…
STONE: A Submodular Optimization Framework for Active 3D Object Detection
Ruiyu Mao, Sarthak Kumar Maharana, Rishabh K Iyer +1
3D object detection is fundamentally important for various emerging applications, including autonomous driving and robotics. A key requirement for training an accurate 3D object de…
Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data
Yuxuan Li, Sarthak Kumar Maharana, Yunhui Guo
With the increasing prevalence of Machine Learning as a Service (MLaaS) platforms, there is a growing focus on deep neural network (DNN) watermarking techniques. These methods are…
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…
Inconsistency-Based Data-Centric Active Open-Set Annotation
Ruiyu Mao, Ouyang Xu, Yunhui Guo
Active learning is a commonly used approach that reduces the labeling effort required to train deep neural networks. However, the effectiveness of current active learning methods i…