activity
20162026
most citedConfidence-Aware Learning for Deep Neural Networks

47 citations · 50 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV20231 cited

Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation

Suho Lee, Seungwon Seo, Jihyo Kim +2

Recently, source-free unsupervised domain adaptation (SFUDA) has emerged as a more practical and feasible approach compared to unsupervised domain adaptation (UDA) which assumes th…

cs.CV20236 cited

Rethinking Evaluation Protocols of Visual Representations Learned via Self-supervised Learning

Jae-Hun Lee, Doyoung Yoon, ByeongMoon Ji +2

Linear probing (LP) (and -NN) on the upstream dataset with labels (e.g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate th…

cs.CV2023

Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions

Jihyo Kim, Jeonghyeon Kim, Sangheum Hwang

Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. This benefits especially deep neu…

cs.CV2018

Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge

Mitko Veta, Yujing J. Heng, Nikolas Stathonikos +30

Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Assessment of tumor proliferation in a clinical setting is highly subjective an…

cs.CV20173 cited

Accurate Lung Segmentation via Network-Wise Training of Convolutional Networks

Sangheum Hwang, Sunggyun Park

We introduce an accurate lung segmentation model for chest radiographs based on deep convolutional neural networks. Our model is based on atrous convolutional layers to increase th…

cs.CV2016

Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation

Hyo-Eun Kim, Sangheum Hwang

A weakly-supervised semantic segmentation framework with a tied deconvolutional neural network is presented. Each deconvolution layer in the framework consists of unpooling and dec…