Slight Corruption in Pre-training Data Makes Better Diffusion Models

Slight Corruption in Pre-training Data Makes Better Diffusion Models

30 May 2024

Hao Chen

Xiang Li

Masashi Sugiyama

Bhiksha Raj

Papers citing "Slight Corruption in Pre-training Data Makes Better Diffusion Models"

19 / 19 papers shown

Title
Learning Wheelchair Tennis Navigation from Broadcast Videos with Domain Knowledge Transfer and Diffusion Motion Planning Zixuan Wu Z. Zaidi Adithya Patil Qingyu Xiao Matthew C. Gombolay 56 0 0 29 Sep 2024
Learning Mixtures of Gaussians Using Diffusion Models Khashayar Gatmiry Jonathan A. Kelner Holden Lee 28 13 0 29 Apr 2024
Label-Noise Robust Diffusion Models Byeonghu Na Yeongmin Kim Heesun Bae Jung Hyun Lee Seho Kwon Wanmo Kang Il-Chul Moon NoLa DiffM 42 8 0 27 Feb 2024
On Catastrophic Inheritance of Large Foundation Models Hao Chen Bhiksha Raj Xing Xie Jindong Wang AI4CE 40 12 0 02 Feb 2024
SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise A. Yadav Arjun Singh 33 1 0 03 Dec 2023
Holistic Evaluation of Text-To-Image Models Tony Lee Michihiro Yasunaga Chenlin Meng Yifan Mai Joon Sung Park ... Jun-Yan Zhu Fei-Fei Li Jiajun Wu Stefano Ermon Percy Liang 128 124 0 07 Nov 2023
DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model Xiaofan Li Yifu Zhang Xiaoqing Ye VGen 59 70 0 11 Oct 2023
Text-Only Training for Image Captioning using Noise-Injected CLIP David Nukrai Ron Mokady Amir Globerson VLM CLIP 35 69 0 01 Nov 2022
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions Sitan Chen Sinho Chewi Jungshian Li Yuanzhi Li Adil Salim Anru R. Zhang DiffM 123 245 0 22 Sep 2022
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation Junnan Li Dongxu Li Caiming Xiong S. Hoi MLLM BDL VLM CLIP 380 4,010 0 28 Jan 2022
A Systematic Study of Bias Amplification Melissa Hall L. V. D. van der Maaten Laura Gustafson Maxwell Jones Aaron B. Adcock 80 69 0 27 Jan 2022
Zero-Shot Text-to-Image Generation Aditya A. Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen Ilya Sutskever VLM 253 4,735 0 24 Feb 2021
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts Soravit Changpinyo P. Sharma Nan Ding Radu Soricut VLM 273 845 0 17 Feb 2021
Provably End-to-end Label-Noise Learning without Anchor Points Xuefeng Li Tongliang Liu Bo Han Gang Niu Masashi Sugiyama NoLa 106 119 0 04 Feb 2021
Robust Optimization as Data Augmentation for Large-scale Graphs Kezhi Kong G. Li Mucong Ding Zuxuan Wu Chen Zhu Bernard Ghanem Gavin Taylor Tom Goldstein 87 74 0 19 Oct 2020
Combating noisy labels by agreement: A joint training method with co-regularization Hongxin Wei Lei Feng Xiangyu Chen Bo An NoLa 297 488 0 05 Mar 2020
FreeLB: Enhanced Adversarial Training for Natural Language Understanding Chen Zhu Yu Cheng Zhe Gan S. Sun Tom Goldstein Jingjing Liu AAML 200 430 0 25 Sep 2019
A Style-Based Generator Architecture for Generative Adversarial Networks Tero Karras S. Laine Timo Aila 262 10,183 0 12 Dec 2018
U-Net: Convolutional Networks for Biomedical Image Segmentation Olaf Ronneberger Philipp Fischer Thomas Brox SSeg 3DV 226 74,467 0 18 May 2015