Picture for Kaifeng Chen

Kaifeng Chen

Dataset Distillers Are Good Label Denoisers In the Wild

Add code
Nov 18, 2024
Viaarxiv icon

TIPS: Text-Image Pretraining with Spatial Awareness

Add code
Oct 21, 2024
Figure 1 for TIPS: Text-Image Pretraining with Spatial Awareness
Figure 2 for TIPS: Text-Image Pretraining with Spatial Awareness
Figure 3 for TIPS: Text-Image Pretraining with Spatial Awareness
Figure 4 for TIPS: Text-Image Pretraining with Spatial Awareness
Viaarxiv icon

UDON: Universal Dynamic Online distillatioN for generic image representations

Add code
Jun 12, 2024
Viaarxiv icon

Learning Vision from Models Rivals Learning Vision from Data

Add code
Dec 28, 2023
Figure 1 for Learning Vision from Models Rivals Learning Vision from Data
Figure 2 for Learning Vision from Models Rivals Learning Vision from Data
Figure 3 for Learning Vision from Models Rivals Learning Vision from Data
Figure 4 for Learning Vision from Models Rivals Learning Vision from Data
Viaarxiv icon

Scaling Laws of Synthetic Images for Model Training for Now

Add code
Dec 07, 2023
Figure 1 for Scaling Laws of Synthetic Images for Model Training  for Now
Figure 2 for Scaling Laws of Synthetic Images for Model Training  for Now
Figure 3 for Scaling Laws of Synthetic Images for Model Training  for Now
Figure 4 for Scaling Laws of Synthetic Images for Model Training  for Now
Viaarxiv icon

Improve Supervised Representation Learning with Masked Image Modeling

Add code
Dec 01, 2023
Viaarxiv icon

MatFormer: Nested Transformer for Elastic Inference

Add code
Oct 11, 2023
Viaarxiv icon

Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations

Add code
Sep 04, 2023
Viaarxiv icon

Global Features are All You Need for Image Retrieval and Reranking

Add code
Aug 19, 2023
Figure 1 for Global Features are All You Need for Image Retrieval and Reranking
Figure 2 for Global Features are All You Need for Image Retrieval and Reranking
Figure 3 for Global Features are All You Need for Image Retrieval and Reranking
Figure 4 for Global Features are All You Need for Image Retrieval and Reranking
Viaarxiv icon

Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models

Add code
May 26, 2023
Viaarxiv icon