613 citations · 1.2k across the 67 of their papers we have counts for
10 papers · 1 filter
SeiT++: Masked Token Modeling Improves Storage-efficient Training
Minhyun Lee, Song Park, Byeongho Heo +2
Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-perfo…
Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images
Jiwon Kim, Byeongho Heo, Sangdoo Yun +2
Semantic correspondence methods have advanced to obtaining high-quality correspondences employing complicated networks, aiming to maximize the model capacity. However, despite the…
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…
Switching Temporary Teachers for Semi-Supervised Semantic Segmentation
Jaemin Na, Jung-Woo Ha, Hyung Jin Chang +2
The teacher-student framework, prevalent in semi-supervised semantic segmentation, mainly employs the exponential moving average (EMA) to update a single teacher's weights based on…
Gramian Attention Heads are Strong yet Efficient Vision Learners
Jongbin Ryu, Dongyoon Han, Jongwoo Lim
We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (\ie, classification heads) instead of relying on channel expansion…
Learning with Unmasked Tokens Drives Stronger Vision Learners
Taekyung Kim, Sanghyuk Chun, Byeongho Heo +1
Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tok…
Masking meets Supervision: A Strong Learning Alliance
Byeongho Heo, Taekyung Kim, Sangdoo Yun +1
Pre-training with random masked inputs has emerged as a novel trend in self-supervised training. However, supervised learning still faces a challenge in adopting masking augmentati…
GeNAS: Neural Architecture Search with Better Generalization
Joonhyun Jeong, Joonsang Yu, Geondo Park +2
Neural Architecture Search (NAS) aims to automatically excavate the optimal network architecture with superior test performance. Recent neural architecture search (NAS) approaches…
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…
Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Dongyoon Han, Junsuk Choe, Seonghyeok Chun +5
Supervised learning of image classifiers distills human knowledge into a parametric model through pairs of images and corresponding labels (X,Y). We argue that this simple and wide…