477 citations · 972 across the 72 of their papers we have counts for
82 papers
Identity-Conditioned Score Fusion for Open-Set Person Re-Identification
Manyi Yao, Jurijs Nazarovs, Eunji Chong +6
Robust person re-identification often combines complementary cues such as face, gait, and body shape. While adaptive fusion typically targets query quality, model strength also var…
LINGUAL: Language-INtegrated GUidance in Active Learning for Medical Image Segmentation
Md Shazid Islam, Shreyangshu Bera, Sudipta Paul +1
Although active learning (AL) in segmentation tasks enables experts to annotate selected regions of interest (ROIs) instead of entire images, it remains highly challenging, labor-i…
Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
Hasin Us Sami, Swapneel Sen, Amit K. Roy-Chowdhury +2
Federated learning (FL) allows multiple data-owners to collaboratively train machine learning models by exchanging local gradients, while keeping their private data on-device. To s…
Egocentric and Exocentric Methods: A Short Survey
Anirudh Thatipelli, Shao-Yuan Lo, Amit K. Roy-Chowdhury
Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is…
POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation
Arindam Dutta, Rohit Lal, Yash Garg +4
Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision. However, these algorithms ex…
SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning
Jianpeng Yao, Xiaopan Zhang, Yu Xia +3
Reinforcement learning (RL) enables social robots to generate trajectories without relying on human-designed rules or interventions, making it generally more effective than rule-ba…
Cross-Modal Safety Alignment: Is textual unlearning all you need?
Trishna Chakraborty, Erfan Shayegani, Zikui Cai +5
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing…
Plug-and-Play Transformer Modules for Test-Time Adaptation
Xiangyu Chang, Sk Miraj Ahmed, Srikanth V. Krishnamurthy +4
Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules with…
FLASH: Federated Learning Across Simultaneous Heterogeneities
Xiangyu Chang, Sk Miraj Ahmed, Srikanth V. Krishnamurthy +4
The key premise of federated learning (FL) is to train ML models across a diverse set of data-owners (clients), without exchanging local data. An overarching challenge to this date…
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
Sk Miraj Ahmed, Fahim Faisal Niloy, Xiangyu Chang +3
Adapting to dynamic data distributions is a practical yet challenging task. One effective strategy is to use a model ensemble, which leverages the diverse expertise of different mo…
STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation
Rohit Lal, Saketh Bachu, Yash Garg +6
The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition, gait recognition, and virtual/augmented reality. However, a persisten…
Repurposing SAM for User-Defined Semantics Aware Segmentation
Rohit Kundu, Sudipta Paul, Arindam Dutta +1
The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific o…
POISE: Pose Guided Human Silhouette Extraction under Occlusions
Arindam Dutta, Rohit Lal, Dripta S. Raychaudhuri +2
Human silhouette extraction is a fundamental task in computer vision with applications in various downstream tasks. However, occlusions pose a significant challenge, leading to inc…
Effective Restoration of Source Knowledge in Continual Test Time Adaptation
Fahim Faisal Niloy, Sk Miraj Ahmed, Dripta S. Raychaudhuri +2
Traditional test-time adaptation (TTA) methods face significant challenges in adapting to dynamic environments characterized by continuously changing long-term target distributions…
Learning Deformable 3D Graph Similarity to Track Plant Cells in Unregistered Time Lapse Images
Md Shazid Islam, Arindam Dutta, Calvin-Khang Ta +5
Tracking of plant cells in images obtained by microscope is a challenging problem due to biological phenomena such as large number of cells, non-uniform growth of different layers…
Prior-guided Source-free Domain Adaptation for Human Pose Estimation
Dripta S. Raychaudhuri, Calvin-Khang Ta, Arindam Dutta +2
Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data during adaptation, which can be challenging due to privacy, memory, or…
SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets
Cody Simons, Dripta S. Raychaudhuri, Sk Miraj Ahmed +3
Scene understanding using multi-modal data is necessary in many applications, e.g., autonomous navigation. To achieve this in a variety of situations, existing models must be able…
Efficient Controllable Multi-Task Architectures
Abhishek Aich, Samuel Schulter, Amit K. Roy-Chowdhury +2
We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This ena…
FedYolo: Augmenting Federated Learning with Pretrained Transformers
Xuechen Zhang, Mingchen Li, Xiangyu Chang +4
The growth and diversity of machine learning applications motivate a rethinking of learning with mobile and edge devices. How can we address diverse client goals and learn with sca…
Collaborative Multi-Agent Video Fast-Forwarding
Shuyue Lan, Zhilu Wang, Ermin Wei +2
Multi-agent applications have recently gained significant popularity. In many computer vision tasks, a network of agents, such as a team of robots with cameras, could work collabor…
Cross-Domain Video Anomaly Detection without Target Domain Adaptation
Abhishek Aich, Kuan-Chuan Peng, Amit K. Roy-Chowdhury
Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source t…
GAMA: Generative Adversarial Multi-Object Scene Attacks
Abhishek Aich, Calvin-Khang Ta, Akash Gupta +4
The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes includ…
AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
Sudipta Paul, Amit K. Roy-Chowdhury, Anoop Cherian
Recent years have seen embodied visual navigation advance in two distinct directions: (i) in equipping the AI agent to follow natural language instructions, and (ii) in making the…
Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks
Abhishek Aich, Shasha Li, Chengyu Song +3
State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings,…