22 citations · 60 across the 22 of their papers we have counts for
28 papers
FairRSFM: A Biome-Aware Benchmark and Debiasing Framework for Remote Sensing Foundation Models
Md Aminur Hossain, Omkumar Vaghasiya, Rajeev Ranjan Dwivedi +2
Remote sensing foundation models (RSFMs) are commonly evaluated using aggregate metrics, which can hide systematic performance disparities across ecological regions. We introduce F…
AlignJEPA: Predictive Vision-Language Alignment for Remote Sensing Foundation Models
Md Aminur Hossain, Omkumar Vaghasiya, Rajeev Ranjan Dwivedi +2
Remote sensing (RS) foundation models provide transferable Earth observation representations across sensors, resolutions, and geographies, yet most remain weakly aligned with natur…
Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift
Ashish Anand Shukla, Rini Smita Thakur, Aryan Das +1
Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA),…
Histogram Assisted Quality Aware Generative Model for Resolution Invariant NIR Image Colorization
Abhinav Attri, Rajeev Ranjan Dwivedi, Samiran Das +1
We present HAQAGen, a unified generative model for resolution-invariant NIR-to-RGB colorization that balances chromatic realism with structural fidelity. The proposed model introdu…
CLFSeg: A Fuzzy-Logic based Solution for Boundary Clarity and Uncertainty Reduction in Medical Image Segmentation
Anshul Kaushal, Kunal Jangid, Vinod K. Kurmi
Accurate polyp and cardiac segmentation for early detection and treatment is essential for the diagnosis and treatment planning of cancer-like diseases. Traditional convolutional n…
Grad-CL: Source Free Domain Adaptation with Gradient Guided Feature Disalignment
Rini Smita Thakur, Rajeev Ranjan Dwivedi, Vinod K Kurmi
Accurate segmentation of the optic disc and cup is critical for the early diagnosis and management of ocular diseases such as glaucoma. However, segmentation models trained on one…
Multi Attribute Bias Mitigation via Representation Learning
Rajeev Ranjan Dwivedi, Ankur Kumar, Vinod K Kurmi
Real world images frequently exhibit multiple overlapping biases, including textures, watermarks, gendered makeup, scene object pairings, etc. These biases collectively impair the…
Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning
Parinita Nema, Vinod K Kurmi
Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existi…
Label Calibration in Source Free Domain Adaptation
Shivangi Rai, Rini Smita Thakur, Kunal Jangid +1
Source-free domain adaptation (SFDA) utilizes a pre-trained source model with unlabeled target data. Self-supervised SFDA techniques generate pseudolabels from the pre-trained sour…
Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation
Rini Smita Thakur, Vinod K. Kurmi
Semi-supervised (SS) semantic segmentation exploits both labeled and unlabeled images to overcome tedious and costly pixel-level annotation problems. Pseudolabel supervision is one…
CosFairNet:A Parameter-Space based Approach for Bias Free Learning
Rajeev Ranjan Dwivedi, Priyadarshini Kumari, Vinod K Kurmi
Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bi…
Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation
Riyansha Singh, Parinita Nema, Vinod K Kurmi
In machine learning applications, gradual data ingress is common, especially in audio processing where incremental learning is vital for real-time analytics. Few-shot class-increme…
Gradient Based Activations for Accurate Bias-Free Learning
Vinod K Kurmi, Rishabh Sharma, Yash Vardhan Sharma +1
Bias mitigation in machine learning models is imperative, yet challenging. While several approaches have been proposed, one view towards mitigating bias is through adversarial lear…
Prb-GAN: A Probabilistic Framework for GAN Modelling
Blessen George, Vinod K. Kurmi, Vinay P. Namboodiri
Generative adversarial networks (GANs) are very popular to generate realistic images, but they often suffer from the training instability issues and the phenomenon of mode loss. In…
Exploring Dropout Discriminator for Domain Adaptation
Vinod K Kurmi, Venkatesh K Subramanian, Vinay P. Namboodiri
Adaptation of a classifier to new domains is one of the challenging problems in machine learning. This has been addressed using many deep and non-deep learning based methods. Among…
Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning
Indu Joshi, Ayush Utkarsh, Riya Kothari +4
A fingerprint region of interest (roi) segmentation algorithm is designed to separate the foreground fingerprint from the background noise. All the learning based state-of-the-art…
Data Uncertainty Guided Noise-aware Preprocessing Of Fingerprints
Indu Joshi, Ayush Utkarsh, Riya Kothari +4
The effectiveness of fingerprint-based authentication systems on good quality fingerprints is established long back. However, the performance of standard fingerprint matching syste…
Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
Shanu Kumar, Vinod Kumar Kurmi, Praphul Singh +1
Understanding unsupervised domain adaptation has been an important task that has been well explored. However, the wide variety of methods have not analyzed the role of a classifier…
Collaborative Learning to Generate Audio-Video Jointly
Vinod K Kurmi, Vipul Bajaj, Badri N Patro +3
There have been a number of techniques that have demonstrated the generation of multimedia data for one modality at a time using GANs, such as the ability to generate images, video…
Domain Impression: A Source Data Free Domain Adaptation Method
Vinod K Kurmi, Venkatesh K Subramanian, Vinay P Namboodiri
Unsupervised Domain adaptation methods solve the adaptation problem for an unlabeled target set, assuming that the source dataset is available with all labels. However, the availab…
Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting
Vinod K Kurmi, Badri N. Patro, Venkatesh K. Subramanian +1
One of the major limitations of deep learning models is that they face catastrophic forgetting in an incremental learning scenario. There have been several approaches proposed to t…
Deep Bayesian Network for Visual Question Generation
Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar +1
Generating natural questions from an image is a semantic task that requires using vision and language modalities to learn multimodal representations. Images can have multiple visua…
Revisiting Paraphrase Question Generator using Pairwise Discriminator
Badri N. Patro, Dev Chauhan, Vinod K. Kurmi +1
In this paper, we propose a method for obtaining sentence-level embeddings. While the problem of securing word-level embeddings is very well studied, we propose a novel method for…
Curriculum based Dropout Discriminator for Domain Adaptation
Vinod Kumar Kurmi, Vipul Bajaj, Venkatesh K Subramanian +1
Domain adaptation is essential to enable wide usage of deep learning based networks trained using large labeled datasets. Adversarial learning based techniques have shown their uti…