13 citations · 31 across the 26 of their papers we have counts for
28 papers
ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching
Prashant Pandey, Devineni Sri Venkatraya Chowdary, Brejesh Lall
Diffusion models for structured scientific generation must produce samples satisfying hard geometric constraints imposed by physics, chemistry, or biology, yet inference in these s…
On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos
Darakshan Rashid, Raza Imam, Ufaq Khan +9
Temporal vision-language models (TVLMs) offer a reusable, prompt-based interface for surgical video understanding, yet, their robustness under clinically realistic acquisition arti…
Can Experts Adapt Without Training? On Test-Time Modality Generalization in MVLMs
Raza Imam, Darakshan Rashid, Yutong Xie +3
Medical vision-language models (MVLMs) promise broad zero-shot generalization, yet their reliability collapses when confronted with unseen modalities and domains, precisely where c…
T-CLIP: Enabling Thermal Perception for Contrastive Language-Image Pretraining
Tayeba Qazi, Ayush Maheshwari, Prerana Mukherjee +1
Thermal imaging offers a powerful alternative to visible-spectrum vision under challenging conditions such as low illumination and adverse weather, yet foundational vision-language…
Continual Segmentation under Joint Nonstationarity
Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary +1
Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneous…
Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement
Jyotirmoy Nath, Neeraj Kumar, Brejesh Lall
Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, most existing methods treat each task's prompt as a monolithic, instance-b…
Unified Multi-Dataset Training for TBPS
Nilanjana Chatterjee, Sidharatha Garg, A V Subramanyam +1
Text-Based Person Search (TBPS) has seen significant progress with vision-language models (VLMs), yet it remains constrained by limited training data and the fact that VLMs are not…
Improving Clinical Imaging Systems using Cognition based Approaches
Kailas Dayanandan, Brejesh Lall
Clinical systems operate in safety-critical environments and are not intended to function autonomously; however, they are currently designed to replicate clinicians' diagnoses rath…
Leveraging band diversity for feature selection in EO data
Sadia Hussain, Brejesh Lall
Hyperspectral imaging (HSI) is a powerful earth observation technology that captures and processes information across a wide spectrum of wavelengths. Hyperspectral imaging provides…
Optimizing Vision Transformers with Data-Free Knowledge Transfer
Gousia Habib, Damandeep Singh, Ishfaq Ahmad Malik +1
The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to…
Dual Thinking and Logical Processing -- Are Multi-modal Large Language Models Closing the Gap with Human Vision ?
Kailas Dayanandan, Nikhil Kumar, Anand Sinha +1
The dual thinking framework considers fast, intuitive, and slower logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and…
A Comprehensive Review of Knowledge Distillation in Computer Vision
Gousia Habib, Tausifa jan Saleem, Sheikh Musa Kaleem +2
Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent…
Insights into the Lottery Ticket Hypothesis and Iterative Magnitude Pruning
Tausifa Jan Saleem, Ramanjit Ahuja, Surendra Prasad +1
Lottery ticket hypothesis for deep neural networks emphasizes the importance of initialization used to re-train the sparser networks obtained using the iterative magnitude pruning…
Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN
Neeraj Kumar, Ankur Narang, Brejesh Lall
In this paper, we present a Diffusion GAN based approach (Prosodic Diff-TTS) to generate the corresponding high-fidelity speech based on the style description and content text as a…
LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
Gousia Habib, Tausifa Jan Saleem, Ishfaq Ahmad Malik +1
With the rapid development of computer vision, Vision Transformers (ViTs) offer the tantalising prospect of unified information processing across visual and textual domains due to…
Transformer-based Nonlinear Equalization for DP-16QAM Coherent Optical Communication Systems
Naveenta Gautam, Sai Vikranth Pendem, Brejesh Lall +1
Compensating for nonlinear effects using digital signal processing (DSP) is complex and computationally expensive in long-haul optical communication systems due to intractable inte…
IIITD-20K: Dense captioning for Text-Image ReID
A V Subramanyam, Niranjan Sundararajan, Vibhu Dubey +1
Text-to-Image (T2I) ReID has attracted a lot of attention in the recent past. CUHK-PEDES, RSTPReid and ICFG-PEDES are the three available benchmarks to evaluate T2I ReID methods. R…
A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentation
Prashant Pandey, Mustafa Chasmai, Monish Natarajan +1
Increasing attention is being diverted to data-efficient problem settings like Open Vocabulary Semantic Segmentation (OVSS) which deals with segmenting an arbitrary object that may…
Knowledge Distillation in Vision Transformers: A Critical Review
Gousia Habib, Tausifa Jan Saleem, Brejesh Lall
In Natural Language Processing (NLP), Transformers have already revolutionized the field by utilizing an attention-based encoder-decoder model. Recently, some pioneering works have…
KL Regularized Normalization Framework for Low Resource Tasks
Neeraj Kumar, Ankur Narang, Brejesh Lall
Large pre-trained models, such as Bert, GPT, and Wav2Vec, have demonstrated great potential for learning representations that are transferable to a wide variety of downstream tasks…
Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs
Prashant Pandey, Aleti Vardhan, Mustafa Chasmai +2
Few-shot Learning (FSL) methods are being adopted in settings where data is not abundantly available. This is especially seen in medical domains where the annotations are expensive…
Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs
Prashant Pandey, Mustafa Chasmai, Tanuj Sur +1
Despite the tremendous progress made by deep learning models in image semantic segmentation, they typically require large annotated examples, and increasing attention is being dive…
Altering Backward Pass Gradients improves Convergence
Bishshoy Das, Milton Mondal, Brejesh Lall +2
In standard neural network training, the gradients in the backward pass are determined by the forward pass. As a result, the two stages are coupled. This is how most neural network…
ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
Vinay Kaushik, Kartik Jindgar, Brejesh Lall
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is lea…