activity
20212026
most citedTTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation

21 citations · 25 across the 10 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Jooyeol Yun, Jintae Park, Hyesu Lim +3

Recovering an editable design file from a raster image is a common and costly bottleneck in modern design workflows, yet remains challenging since editability depends on recovering…

cs.CV2025

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

Jinho Choi, Hyesu Lim, Steffen Schneider +1

Dataset bias, where data points are skewed to certain concepts, is ubiquitous in machine learning datasets. Yet, systematically identifying these biases is challenging without cost…

cs.CV2025

CytoSAE: Interpretable Cell Embeddings for Hematology

Muhammed Furkan Dasdelen, Hyesu Lim, Michele Buck +3

Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Very recently, SAEs were also adopted for the visual…

cs.CV2024★ 2 cited

Sparse autoencoders reveal selective remapping of visual concepts during adaptation

Hyesu Lim, Jinho Choi, Jaegul Choo +1

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mec…

cs.CV2023★ 1 cited

Towards Calibrated Robust Fine-Tuning of Vision-Language Models

Changdae Oh, Hyesu Lim, Mijoo Kim +6

Improving out-of-distribution (OOD) generalization during in-distribution (ID) adaptation is a primary goal of robust fine-tuning of zero-shot models beyond naive fine-tuning. Howe…

cs.CV2023★ 21 cited

TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation

Hyesu Lim, Byeonggeun Kim, Jaegul Choo +1

This paper proposes a novel batch normalization strategy for test-time adaptation. Recent test-time adaptation methods heavily rely on the modified batch normalization, i.e., trans…