3 citations · 3 across the 19 of their papers we have counts for
20 papers
Technical note on: Zero-Training Feature-Space Alignment via Information Geometry
Behraj Khan, Tahir Qasim Syed, Syed Ahmad Chan Bukhari
Deep vision models often degrade under distribution shift. Test-time adaptation can improve robustness but typically requires iterative optimization, hyperparameter tuning, and mul…
CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation
Behraj Khan, Shabir Ahmad, Syed Ahmad Chan Bukhari +1
Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under interventions, supporting down…
PIcsC: Partitioning-Induced Covariate Shift Correction
Behraj Khan, Behroz Mirza, Syed Ahmad Chan Bukhari +1
Covariate shift across training-data partitions biases model selection and parameter estimation in cross-validation, lifelong learning, and federated learning. We propose \textit{P…
Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images
Annayah Usman, Behraj Khan, Tahir Qasim Syed
Precise volumetric delineation of hippocampal structures is essential for quantifying neurodevelopmental trajectories in pre-term and term infants, where subtle morphological varia…
Clinically-aligned ischemic stroke segmentation and ASPECTS scoring on NCCT imaging using a slice-gated loss on foundation representations
Hiba Azeem, Behraj Khan, Tahir Qasim Syed
Rapid infarct assessment on non-contrast CT (NCCT) is essential for acute ischemic stroke management. Most deep learning methods perform pixel-wise segmentation without modeling th…
Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation
Tahir Qasim Syed, Behraj Khan
Often, constraints arise in deployment settings where even lightweight parameter updates e.g. parameter-efficient fine-tuning could induce model shift or tuning instability. We stu…
Technical note on Fisher Information for Robust Federated Cross-Validation
Behraj Khan, Tahir Qasim Syed
When training data are fragmented across batches or federated-learned across different geographic locations, trained models manifest performance degradation. That degradation partl…
Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting
Behraj Khan, Tahir Qasim Syed
We present a theoretical framework for M-FISHER, a method for sequential distribution shift detection and stable adaptation in streaming data. For detection, we construct an expone…
Confidence-Calibrating Regularization for Robust Brain MRI Segmentation Under Domain Shift
Behraj Khan, Tahir Qasim Syed, Syed Ahmad Chan Bukhari
The Segment Anything Model (SAM) exhibits strong zero-shot performance on natural images but suffers from domain shift and overconfidence when applied to medical volumes. We propos…
Adapting to Fragmented and Evolving Data: A Fisher Information Perspective
Behraj Khan, Tahir Qasim Syed, Nouman Muhammad Durrani
Modern machine learning systems operating in dynamic environments often face \textit{sequential covariate shift} (SCS), where input distributions evolve over time while the conditi…
Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift
Behraj Khan, Tahir Qasim Syed, Nouman M. Durrani +3
Foundation models like CLIP and SAM have advanced computer vision and medical imaging via low-shot transfer learning, aiding CADD with limited data. However, their deployment faces…
An agentic system with reinforcement-learned subsystem improvements for parsing form-like documents
Ayesha Amjad, Saurav Sthapit, Tahir Qasim Syed
Extracting alphanumeric data from form-like documents such as invoices, purchase orders, bills, and financial documents is often performed via vision (OCR) and learning algorithms…
Efficient Learning Under Density Shift in Incremental Settings Using Cramér-Rao-Based Regularization
Behraj Khan, Behroz Mirza, Nouman Durrani +1
The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenge…
Multimodal HIE Lesion Segmentation in Neonates: A Comparative Study of Loss Functions
Annayah Usman, Abdul Haseeb, Tahir Syed
Segmentation of Hypoxic-Ischemic Encephalopathy (HIE) lesions in neonatal MRI is a crucial but challenging task due to diffuse multifocal lesions with varying volumes and the limit…
Latents of latents to delineate pixels: hybrid Matryoshka autoencoder-to-U-Net pairing for segmenting large medical images in GPU-poor and low-data regimes
Tahir Syed, Ariba Khan, Sawera Hanif
Medical images are often high-resolution and lose important detail if downsampled, making pixel-level methods such as semantic segmentation much less efficient if performed on a lo…
Causal Covariate Shift Correction using Fisher information penalty
Behraj Khan, Behroz Mirza, Tahir Syed
Evolving feature densities across batches of training data bias cross-validation, making model selection and assessment unreliable (\cite{sugiyama2012machine}). This work takes a d…
Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models
Behraj Khan, Rizwan Qureshi, Nouman Muhammad Durrani +1
Since the establishment of vision-language foundation models as the new mainstay in low-shot vision classification tasks, the question of domain generalization arising from insuffi…
Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models
Behraj Khan, Tahir Syed
Confidence calibration is an emerging challenge in real-world decision systems based on foundations models when used for downstream vision classification tasks. Due to various reas…
Mitigating covariate shift in non-colocated data with learned parameter priors
Behraj Khan, Behroz Mirza, Nouman Durrani +1
When training data are distributed across{ time or space,} covariate shift across fragments of training data biases cross-validation, compromising model selection and assessment. W…
Textual analysis of End User License Agreement for red-flagging potentially malicious software
Behraj Khan, Tahir Syed, Zeshan Khan +1
New software and updates are downloaded by end users every day. Each dowloaded software has associated with it an End Users License Agreements (EULA), but this is rarely read. An E…