Alert button
Picture for Sangdoo Yun

Sangdoo Yun

Alert button

Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models

May 24, 2023
Geewook Kim, Hodong Lee, Daehee Kim, Haeji Jung, Sanghee Park, Yoonsik Kim, Sangdoo Yun, Taeho Kil, Bado Lee, Seunghyun Park

Figure 1 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Figure 2 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Figure 3 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Figure 4 for Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models
Viaarxiv icon

Who Wrote this Code? Watermarking for Code Generation

May 24, 2023
Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, Gunhee Kim

Figure 1 for Who Wrote this Code? Watermarking for Code Generation
Figure 2 for Who Wrote this Code? Watermarking for Code Generation
Figure 3 for Who Wrote this Code? Watermarking for Code Generation
Figure 4 for Who Wrote this Code? Watermarking for Code Generation
Viaarxiv icon

What Do Self-Supervised Vision Transformers Learn?

May 01, 2023
Namuk Park, Wonjae Kim, Byeongho Heo, Taekyung Kim, Sangdoo Yun

Figure 1 for What Do Self-Supervised Vision Transformers Learn?
Figure 2 for What Do Self-Supervised Vision Transformers Learn?
Figure 3 for What Do Self-Supervised Vision Transformers Learn?
Figure 4 for What Do Self-Supervised Vision Transformers Learn?
Viaarxiv icon

RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models

Apr 21, 2023
Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun, Jin Young Choi

Figure 1 for RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models
Figure 2 for RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models
Figure 3 for RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models
Figure 4 for RoCOCO: Robust Benchmark MS-COCO to Stress-test Robustness of Image-Text Matching Models
Viaarxiv icon

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

Apr 10, 2023
Gyeongsik Moon, Hongsuk Choi, Sanghyuk Chun, Jiyoung Lee, Sangdoo Yun

Figure 1 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild
Figure 2 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild
Figure 3 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild
Figure 4 for Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild
Viaarxiv icon

Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts

Apr 04, 2023
Dongyoon Han, Junsuk Choe, Seonghyeok Chun, John Joon Young Chung, Minsuk Chang, Sangdoo Yun, Jean Y. Song, Seong Joon Oh

Figure 1 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Figure 2 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Figure 3 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Figure 4 for Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts
Viaarxiv icon

Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts

Mar 30, 2023
Dongyoon Han, Junsuk Choe, Seonghyeok Chun, John Joon Young Chung, Minsuk Chang, Sangdoo Yun, Jean Y. Song, Seong Joon Oh

Figure 1 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Figure 2 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Figure 3 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Figure 4 for Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts
Viaarxiv icon

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

Mar 21, 2023
Geonmo Gu, Sanghyuk Chun, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun

Figure 1 for CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Figure 2 for CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Figure 3 for CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Figure 4 for CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Viaarxiv icon

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Mar 20, 2023
Song Park, Sanghyuk Chun, Byeongho Heo, Wonjae Kim, Sangdoo Yun

Figure 1 for SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
Figure 2 for SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
Figure 3 for SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
Figure 4 for SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage
Viaarxiv icon

Neural Relation Graph for Identifying Problematic Data

Jan 29, 2023
Jang-Hyun Kim, Sangdoo Yun, Hyun Oh Song

Figure 1 for Neural Relation Graph for Identifying Problematic Data
Figure 2 for Neural Relation Graph for Identifying Problematic Data
Figure 3 for Neural Relation Graph for Identifying Problematic Data
Figure 4 for Neural Relation Graph for Identifying Problematic Data
Viaarxiv icon