collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2025

High-Frequency First: A Two-Stage Approach for Improving Image INR

Sumit Kumar Dam, Mrityunjoy Gain, Eui-Nam Huh +1

Implicit Neural Representations (INRs) have emerged as a powerful alternative to traditional pixel-based formats by modeling images as continuous functions over spatial coordinates…

cs.CV2025

FedFeat+: A Robust Federated Learning Framework Through Federated Aggregation and Differentially Private Feature-Based Classifier Retraining

Mrityunjoy Gain, Kitae Kim, Avi Deb Raha +4

In this paper, we propose the FedFeat+ framework, which distinctively separates feature extraction from classification. We develop a two-tiered model training process: following lo…

cs.CV2024

Boosting Federated Domain Generalization: Understanding the Role of Advanced Pre-Trained Architectures

Avi Deb Raha, Apurba Adhikary, Mrityunjoy Gain +2

In this study, we explore the efficacy of advanced pre-trained architectures, such as Vision Transformers (ViT), ConvNeXt, and Swin Transformers in enhancing Federated Domain Gener…

cs.CV2024

CCC++: Optimized Color Classified Colorization with Segment Anything Model (SAM) Empowered Object Selective Color Harmonization

Mrityunjoy Gain, Avi Deb Raha, Rameswar Debnath

In this paper, we formulate the colorization problem into a multinomial classification problem and then apply a weighted function to classes. We propose a set of formulas to transf…

cs.CV2024

CCC: Color Classified Colorization

Mrityunjoy Gain, Avi Deb Raha, Rameswar Debnath

Automatic colorization of gray images with objects of different colors and sizes is challenging due to inter- and intra-object color variation and the small area of the main object…