activity
20172023
most citedReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

164 citations · 435 across the 12 of their papers we have counts for

collaborators

24 papers

cs.CL20231 cited

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction

Chen-Yu Lee, Chun-Liang Li, Hao Zhang +13

The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that…

cs.LG20229 cited

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Jinsung Yoon, Kihyuk Sohn, Chun-Liang Li +2

Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled. We propose a canonical framework: Semi-supervised Pseudo-la…

cs.CV202211 cited

Visual Prompt Tuning for Generative Transfer Learning

Kihyuk Sohn, Yuan Hao, José Lezama +5

Transferring knowledge from an image synthesis model trained on a large dataset is a promising direction for learning generative image models from various domains efficiently. Whil…

cs.LG20225 cited

Federated Semi-Supervised Learning with Prototypical Networks

Woojung Kim, Keondo Park, Kihyuk Sohn +2

With the increasing computing power of edge devices, Federated Learning (FL) emerges to enable model training without privacy concerns. The majority of existing studies assume the…

cs.LG20221 cited

Towards Group Robustness in the presence of Partial Group Labels

Vishnu Suresh Lokhande, Kihyuk Sohn, Jinsung Yoon +3

Learning invariant representations is an important requirement when training machine learning models that are driven by spurious correlations in the datasets. These spurious correl…

cs.CV202116 cited

Object-aware Contrastive Learning for Debiased Scene Representation

Sangwoo Mo, Hyunwoo Kang, Kihyuk Sohn +2

Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentati…