Sanghyun Jo

icon indicating a website link https://scholar.google.com/citations?user=xgP6q2YAAAAJ&hl=en

icon company OGQ · SNU AIBL Lab icon location South Korea icon location Building interpretable, label-efficient, and multimodal AI systems. AI Researcher at OGQ, advised by Prof. Kyungsu Kim (SNU AIBL Lab).

Results 5 repositories owned by Sanghyun Jo

PuzzleCAM

169
Stars
46
Forks
Watchers

[ICIP 2021] Puzzle-CAM: Improved localization via matching partial and full features.

verified publisher icon shjo-april

RecurSeed_and_EdgePredictMix

44
Stars
8
Forks
Watchers

[Under Review] RecurSeed and EdgePredictMix: Single-stage learning is sufficient for Weakly-Supervised Semantic Segmentation

verified publisher icon shjo-april

Tensorflow_Improving_Pairwise_Ranking_for_Multi-label_Image_Classification

20
Stars
5
Forks
Watchers

[Re-implementation] Improving Pairwise Ranking for Multi-label Image Classification (CVPR2017)

verified publisher icon shjo-april

Tensorflow_RetinaFace

25
Stars
11
Forks
Watchers

[Re-implementation] RetinaFace: Single-stage Dense Face Localisation in the Wild

verified publisher icon shjo-april

MARS

20
Stars
0
Forks
Watchers

[ICCV 2023] MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation

verified publisher icon shjo-april