paper-with-me

Papers

Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks

2023-08-13 · David Junhao Zhang, Mutian Xu, Chuhui Xue, Wenqing Zhang, Xiaoguang Han, Song Bai, Mike Zheng Shou

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy. Recently, synthetic images generated by text-to-image diffusion models, have shown great potential for benefiting image recognition. Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images. To address this, we start by uncovering that diffusion models' cross-attention layers inherently provide annotation-free attention masks aligned with corresponding text inputs on generated images. We then investigate the problems of three prevalent unsupervised learning techniques ( i.e., contrastive learning, masked modeling, and vision-language pretraining) and introduce customized solutions by fully exploiting the aforementioned free attention masks. Our approach is validated through extensive experiments that show consistent improvements in baseline models across various downstream tasks, including image classification, detection, segmentation, and image-text retrieval. By utilizing our method, it is possible to close the performance gap between unsupervised pretraining on synthetic data and real-world scenarios.

📄 PDF Abstract BibTeX arXiv:2308.06739

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learningimage-classificationImage ClassificationImage-text RetrievalRetrievalText Retrieval

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising Process

2024-09-11 · Yang Luo, Yiheng Zhang, Zhaofan Qiu, Ting Yao 외

The emergence of text-to-image generation models has led to the recognition that image enhancement, performed as post-processing, would significantly improve the visual quality of the generated images. Exploring diffusio…

DenoisingImage EnhancementImage GenerationText to Image Generation+1

SafeCFG: Redirecting Harmful Classifier-Free Guidance for Safe Generation

2024-12-20 · Jiadong Pan, Hongcheng Gao, Liang Li, Zheng-Jun Zha 외

Diffusion models (DMs) have demonstrated exceptional performance in text-to-image (T2I) tasks, leading to their widespread use. With the introduction of classifier-free guidance (CFG), the quality of images generated by …

Image Generation

Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection

2024-07-09 · Sergio Naval Marimont, Vasilis Siomos, Matthew Baugh, Christos Tzelepis 외

Unsupervised Anomaly Detection (UAD) methods aim to identify anomalies in test samples comparing them with a normative distribution learned from a dataset known to be anomaly-free. Approaches based on generative models o…

Anomaly DetectionUnsupervised Anomaly Detection

Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Ultrasound Imaging

2024-11-06 · Yuan Bi, Lucie Huang, Ricarda Clarenbach, Reza Ghotbi 외

Ultrasound (US) imaging is widely used in routine clinical practice due to its advantages of being radiation-free, cost-effective, and portable. However, the low reproducibility and quality of US images, combined with th…

Anomaly DetectioncounterfactualUnsupervised Anomaly Detection

Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration

2024-09-05 · Pei Wang, Xiaotong Luo, Yuan Xie, Yanyun Qu

Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices. Data-free distillation provides an …

Image RestorationKnowledge Distillation