331 citations · 462 across the 14 of their papers we have counts for
14 papers
Relevance-Aware Rule: Structural Deletion of Irrelevant Conditions in Decision Trees
Jung-Sik Hong, Jeongeon Lee, Min Kyu Sim +1
Decision trees generate interpretable if--then rules, yet they contain irrelevant conditions (IRCs). These IRCs arise from the structural mechanism of tree splitting and persist ev…
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…
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…
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…
A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
Jihyo Kim, Jiin Koo, Sangheum Hwang
Deep neural networks have achieved outstanding performance over various tasks, but they have a critical issue: over-confident predictions even for completely unknown samples. Many…
Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation
Jeongeun Park, Seungyoun Shin, Sangheum Hwang +1
Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori. Our proposed…
Confidence-Aware Learning for Deep Neural Networks
Jooyoung Moon, Jihyo Kim, Younghak Shin +1
Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many re…
Self-Knowledge Distillation with Progressive Refinement of Targets
Kyungyul Kim, ByeongMoon Ji, Doyoung Yoon +1
The generalization capability of deep neural networks has been substantially improved by applying a wide spectrum of regularization methods, e.g., restricting function space, injec…
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…
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…
A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology
Kyunghyun Paeng, Sangheum Hwang, Sunggyun Park +1
We present a unified framework to predict tumor proliferation scores from breast histopathology whole slide images. Our system offers a fully automated solution to predicting both…
Semantic Noise Modeling for Better Representation Learning
Hyo-Eun Kim, Sangheum Hwang, Kyunghyun Cho
Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, ge…
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…
Self-Transfer Learning for Fully Weakly Supervised Object Localization
Sangheum Hwang, Hyo-Eun Kim
Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural ne…