2.3k citations · 3.9k across the 43 of their papers we have counts for
30 papers · 1 filter
Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data
Tarun Kalluri, Jihyeon Lee, Kihyuk Sohn +4
We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of damage assessment from a…
Improve Supervised Representation Learning with Masked Image Modeling
Kaifeng Chen, Daniel Salz, Huiwen Chang +3
Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked i…
Collaborative Score Distillation for Consistent Visual Synthesis
Subin Kim, Kyungmin Lee, June Suk Choi +3
Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting…
StyleDrop: Text-to-Image Generation in Any Style
Kihyuk Sohn, Nataniel Ruiz, Kimin Lee +11
Pre-trained large text-to-image models synthesize impressive images with an appropriate use of text prompts. However, ambiguities inherent in natural language and out-of-distributi…
Learning Disentangled Prompts for Compositional Image Synthesis
Kihyuk Sohn, Albert Shaw, Yuan Hao +5
We study domain-adaptive image synthesis, the problem of teaching pretrained image generative models a new style or concept from as few as one image to synthesize novel images, to…
Video Probabilistic Diffusion Models in Projected Latent Space
Sihyun Yu, Kihyuk Sohn, Subin Kim +1
Despite the remarkable progress in deep generative models, synthesizing high-resolution and temporally coherent videos still remains a challenge due to their high-dimensionality an…
MaskSketch: Unpaired Structure-guided Masked Image Generation
Dina Bashkirova, Jose Lezama, Kihyuk Sohn +2
Recent conditional image generation methods produce images of remarkable diversity, fidelity and realism. However, the majority of these methods allow conditioning only on labels o…
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
Kuniaki Saito, Kihyuk Sohn, Xiang Zhang +4
In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using label…
MAGVIT: Masked Generative Video Transformer
Lijun Yu, Yong Cheng, Kihyuk Sohn +8
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spat…
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…
Prefix Conditioning Unifies Language and Label Supervision
Kuniaki Saito, Kihyuk Sohn, Xiang Zhang +4
Image-classification datasets have been used to pretrain image recognition models. Recently, web-scale image-caption datasets have emerged as a source of powerful pretraining alter…
Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types
Kihyuk Sohn, Jinsung Yoon, Chun-Liang Li +2
We study anomaly clustering, grouping data into coherent clusters of anomaly types. This is different from anomaly detection that aims to divide anomalies from normal data. Unlike…
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…
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
Chun-Liang Li, Kihyuk Sohn, Jinsung Yoon +1
We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage…
CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning
Chen Wei, Kihyuk Sohn, Clayton Mellina +2
Semi-supervised learning on class-imbalanced data, although a realistic problem, has been under studied. While existing semi-supervised learning (SSL) methods are known to perform…
Assessing Post-Disaster Damage from Satellite Imagery using Semi-Supervised Learning Techniques
Jihyeon Lee, Joseph Z. Xu, Kihyuk Sohn +8
To respond to disasters such as earthquakes, wildfires, and armed conflicts, humanitarian organizations require accurate and timely data in the form of damage assessments, which in…
Learning and Evaluating Representations for Deep One-class Classification
Kihyuk Sohn, Chun-Liang Li, Jinsung Yoon +2
We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on lear…
Improving Face Recognition by Clustering Unlabeled Faces in the Wild
Aruni RoyChowdhury, Xiang Yu, Kihyuk Sohn +2
While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reduci…
A Simple Semi-Supervised Learning Framework for Object Detection
Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li +3
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent prog…
Towards Universal Representation Learning for Deep Face Recognition
Yichun Shi, Xiang Yu, Kihyuk Sohn +2
Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domain…
Adaptation Across Extreme Variations using Unlabeled Domain Bridges
Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai +2
We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and…
Active Adversarial Domain Adaptation
Jong-Chyi Su, Yi-Hsuan Tsai, Kihyuk Sohn +3
We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two re…
Domain Adaptation for Structured Output via Discriminative Patch Representations
Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter +1
Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models…
Feature Transfer Learning for Deep Face Recognition with Under-Represented Data
Xi Yin, Xiang Yu, Kihyuk Sohn +2
Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such s…