activity
20162023
most citedVisual Transformer for Task-aware Active Learning

5 citations · 14 across the 13 of their papers we have counts for

collaborators
Showing 2023Show all

9 papers · 1 filter

eess.IV2023

Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining

Bidur Khanal, Binod Bhattarai, Bishesh Khanal +1

Noisy labels hurt deep learning-based supervised image classification performance as the models may overfit the noise and learn corrupted feature extractors. For natural image clas…

cs.CV2023

Neural Network Pruning for Real-time Polyp Segmentation

Suman Sapkota, Pranav Poudel, Sudarshan Regmi +2

Computer-assisted treatment has emerged as a viable application of medical imaging, owing to the efficacy of deep learning models. Real-time inference speed remains a key requireme…

eess.IV2023

M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks

Bidur Khanal, Binod Bhattarai, Bishesh Khanal +2

Acquiring properly annotated data is expensive in the medical field as it requires experts, time-consuming protocols, and rigorous validation. Active learning attempts to minimize…

cs.CV2023

A Client-server Deep Federated Learning for Cross-domain Surgical Image Segmentation

Ronast Subedi, Rebati Raman Gaire, Sharib Ali +3

This paper presents a solution to the cross-domain adaptation problem for 2D surgical image segmentation, explicitly considering the privacy protection of distributed datasets belo…

cs.CV2023

T2FNorm: Extremely Simple Scaled Train-time Feature Normalization for OOD Detection

Sudarshan Regmi, Bibek Panthi, Sakar Dotel +3

Neural networks are notorious for being overconfident predictors, posing a significant challenge to their safe deployment in real-world applications. While feature normalization ha…

cs.CV20233 cited

iEdit: Localised Text-guided Image Editing with Weak Supervision

Rumeysa Bodur, Erhan Gundogdu, Binod Bhattarai +3

Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the gen…