Samrat Mukherjee — accepted AI-conference papers

2025

Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation

Tanuj Sur, Samrat Mukherjee, Kaizer Rahaman, Subhasis Chaudhuri, Muhammad Haris Khan, Biplab Banerjee

CVPR 2025poster

3D point cloud segmentation is essential across a range of applications; however, conventional methods often struggle in evolving environments, particularly when tasked with identifying novel categories under limited supervision. Few-Shot Learning (FSL) and Class Incremental Learning (CIL) have been…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Transforming Code Understanding: Clustering-Based Retrieval for Improved Summarization in Domain-Specific Languages

Baban Gain, Dibyanayan Bandyopadhyay, Samrat Mukherjee, Aryan Sahoo, Saswati Dana, Palanivel Kodeswaran +3

COLING 2025industry

A domain-specific extension of C language known as extended Berkeley Packet Filter (eBPF) has gained widespread acceptance for various tasks, including observability, security, and network acceleration in the cloud community. Due to its recency and complexity, there is an overwhelming need for natur…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

UIDAPLE: Unsupervised Incremental Domain Adaptation through Adaptive Prompt Learning

Samrat Mukherjee, Tanuj Sur, Saurish Seksaria, Subhasis Chaudhuri, Gemma Roig, Biplab Banerjee

ICASSP 2025accepted

Continual learning poses significant challenges for deep neural networks, notably catastrophic forgetting, particularly when faced with shifting data distributions that compromise previously acquired knowledge. This paper tackles these issues within the Unsupervised Incremental Domain Adaptation (UI…

Cited by 0 Source ↗Scholar ↗