1 citations · 2 across the 11 of their papers we have counts for
12 papers
Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models
Sangyoon Bae, Sk Miraj Ahmed, Shinjae Yoo +1
Can we determine whether a foundation model will generalize out-of-distribution (OOD) before any target data is available? Existing diagnostics require source or target data, which…
A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis
Sk Miraj Ahmed, Yuewei Lin, Chuntian Cao +9
Scanning Electron Microscopy (SEM) is indispensable in modern materials science, enabling high-resolution imaging across a wide range of structural, chemical, and functional invest…
Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference
Sk Miraj Ahmed, Xi Yu, Yunqi Li +2
Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, t…
A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury +1
With the growing adoption of data privacy regulations, the ability to erase private or copyrighted information from trained models has become a crucial requirement. Traditional unl…
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…
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…
Cross-Modal Knowledge Transfer Without Task-Relevant Source Data
Sk Miraj Ahmed, Suhas Lohit, Kuan-Chuan Peng +2
Cost-effective depth and infrared sensors as alternatives to usual RGB sensors are now a reality, and have some advantages over RGB in domains like autonomous navigation and remote…
Unsupervised Multi-source Domain Adaptation Without Access to Source Data
Sk Miraj Ahmed, Dripta S. Raychaudhuri, Sujoy Paul +2
Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for an unlabeled domain by transferring knowledge from a separate labeled source domain. However, most of these…
Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning
Sk Miraj Ahmed, Aske R Lejbølle, Rameswar Panda +1
Most of the existing approaches for person re-identification consider a static setting where the number of cameras in the network is fixed. An interesting direction, which has rece…
Least-squares registration of point sets over SE (d) using closed-form projections
Sk. Miraj Ahmed, Niladri Ranjan Das, Kunal Narayan Chaudhury
Consider the problem of registering multiple point sets in some -dimensional space using rotations and translations. Assume that there are sets with common points, and moreover…