15 citations · 18 across the 13 of their papers we have counts for
13 papers
Towards Source-Free Machine Unlearning
Sk Miraj Ahmed, Umit Yigit Basaran, Dripta S. Raychaudhuri +5
As machine learning becomes more pervasive and data privacy regulations evolve, the ability to remove private or copyrighted information from trained models is becoming an increasi…
HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
Trishna Chakraborty, Udita Ghosh, Xiaopan Zhang +5
Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user ins…
SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
Kishor Kumar Bhaumik, Minha Kim, Fahim Faisal Niloy +2
Traffic forecasting in Intelligent Transportation Systems (ITS) is vital for intelligent traffic prediction. Yet, ITS often relies on data from traffic sensors or vehicle devices,…
Source-Free Online Domain Adaptive Semantic Segmentation of Satellite Images under Image Degradation
Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo
Online adaptation to distribution shifts in satellite image segmentation stands as a crucial yet underexplored problem. In this paper, we address source-free and online domain adap…
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…
ODES: Domain Adaptation with Expert Guidance for Online Medical Image Segmentation
Md Shazid Islam, Sayak Nag, Arindam Dutta +4
Unsupervised domain adaptive segmentation typically relies on self-training using pseudo labels predicted by a pre-trained network on an unlabeled target dataset. However, the nois…
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…
HRFNet: High-Resolution Forgery Network for Localizing Satellite Image Manipulation
Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo
Existing high-resolution satellite image forgery localization methods rely on patch-based or downsampling-based training. Both of these training methods have major drawbacks, such…
STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow Prediction
Kishor Kumar Bhaumik, Fahim Faisal Niloy, Saif Mahmud +1
Reliable forecasting of traffic flow requires efficient modeling of traffic data. Indeed, different correlations and influences arise in a dynamic traffic network, making modeling…
CFL-Net: Image Forgery Localization Using Contrastive Learning
Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo
Conventional forgery localizing methods usually rely on different forgery footprints such as JPEG artifacts, edge inconsistency, camera noise, etc., with cross-entropy loss to loca…
Deep Dive into Semi-Supervised ELBO for Improving Classification Performance
Fahim Faisal Niloy, M. Ashraful Amin, AKM Mahbubur Rahman +1
Decomposition of the evidence lower bound (ELBO) objective of VAE used for density estimation revealed the deficiency of VAE for representation learning and suggested ways to impro…
A Novel Disaster Image Dataset and Characteristics Analysis using Attention Model
Fahim Faisal Niloy, Arif, Abu Bakar Siddik Nayem +6
The advancement of deep learning technology has enabled us to develop systems that outperform any other classification technique. However, success of any empirical system depends o…
Attention Toward Neighbors: A Context Aware Framework for High Resolution Image Segmentation
Fahim Faisal Niloy, M. Ashraful Amin, Amin Ahsan Ali +1
High-resolution image segmentation remains challenging and error-prone due to the enormous size of intermediate feature maps. Conventional methods avoid this problem by using patch…