12 citations · 43 across the 12 of their papers we have counts for
14 papers
Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
Junhee Lee, Donghyeon Jeon, Taeoh Kim +2
Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifacts that are misaligned with se…
Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation
Beomyoung Kim, Sung Ju Hwang
Despite significant advances in image segmentation, even state-of-the-art models produce masks with imperfect boundaries, semantic inconsistencies, and structural errors. Mask refi…
ZIM: Zero-Shot Image Matting for Anything
Beomyoung Kim, Chanyong Shin, Joonhyun Jeong +5
The recent segmentation foundation model, Segment Anything Model (SAM), exhibits strong zero-shot segmentation capabilities, but it falls short in generating fine-grained precise m…
HyperCLOVA X Technical Report
Kang Min Yoo, Jaegeun Han, Sookyo In +393
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. H…
Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
Beomyoung Kim, Donghyun Kim, Sung Ju Hwang
This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our…
Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human Matting
Beomyoung Kim, Myeong Yeon Yi, Joonsang Yu +2
This paper presents a new practical training method for human matting, which demands delicate pixel-level human region identification and significantly laborious annotations. To re…
ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
Beomyoung Kim, Joonsang Yu, Sung Ju Hwang
Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task. Despite recent progress with deep learning models, the dynamic n…
The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation
Beomyoung Kim, Joonhyun Jeong, Dongyoon Han +1
In this paper, we introduce a novel learning scheme named weakly semi-supervised instance segmentation (WSSIS) with point labels for budget-efficient and high-performance instance…
EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection
Joonhyun Jeong, Beomyoung Kim, Joonsang Yu +1
This paper analyzes the design choices of face detection architecture that improve efficiency of computation cost and accuracy. Specifically, we re-examine the effectiveness of the…
Learning Features with Parameter-Free Layers
Dongyoon Han, YoungJoon Yoo, Beomyoung Kim +1
Trainable layers such as convolutional building blocks are the standard network design choices by learning parameters to capture the global context through successive spatial opera…
Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement
Beomyoung Kim, Youngjoon Yoo, Chaeeun Rhee +1
Weakly-supervised instance segmentation (WSIS) has been considered as a more challenging task than weakly-supervised semantic segmentation (WSSS). Compared to WSSS, WSIS requires i…
SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
Sungmin Cha, Beomyoung Kim, Youngjoon Yoo +1
This paper introduces a solid state-of-the-art baseline for a class-incremental semantic segmentation (CISS) problem. While the recent CISS algorithms utilize variants of the knowl…
Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation
Beomyoung Kim, Sangeun Han, Junmo Kim
Weakly-supervised semantic segmentation (WSSS) using image-level labels has recently attracted much attention for reducing annotation costs. Existing WSSS methods utilize localizat…
TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection
Beomyoung Kim, Janghyeon Lee, Sihaeng Lee +2
We present a novel approach for oriented object detection, named TricubeNet, which localizes oriented objects using visual cues ( heatmap) instead of oriented box offsets re…