paper-with-me

Papers

DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition

2024-03-08 · Jie Shao, Ke Zhu, Hanxiao Zhang, Jianxin Wu

This paper proposes a new pipeline for long-tail (LT) recognition. Instead of re-weighting or re-sampling, we utilize the long-tailed dataset itself to generate a balanced proxy that can be optimized through cross-entropy (CE). Specifically, a randomly initialized diffusion model, trained exclusively on the long-tailed dataset, is employed to synthesize new samples for underrepresented classes. Then, we utilize the inherent information in the original dataset to filter out harmful samples and keep the useful ones. Our strategy, Diffusion model for Long-Tail recognition (DiffuLT), represents a pioneering utilization of generative models in long-tail recognition. DiffuLT achieves state-of-the-art results on CIFAR10-LT, CIFAR100-LT, and ImageNet-LT, surpassing the best competitors with non-trivial margins. Abundant ablations make our pipeline interpretable, too. The whole generation pipeline is done without any external data or pre-trained model weights, making it highly generalizable to real-world long-tailed settings.

📄 PDF Abstract BibTeX arXiv:2403.05170

Code (0)

등록된 구현이 없습니다.

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

Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection

2025-01-10 · Yu-Cheng Chou, Gary Y. Li, Li Chen, Mohsen Zahiri 외

Developing reliable healthcare AI models requires training with representative and diverse data. In imbalanced datasets, model performance tends to plateau on the more prevalent classes while remaining low on less common…

AnatomyDiversityImage Generation

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

2025-07-11 · Fang Chen, Alex Villa, Gongbo Liang, Fuxing Li 외 arxiv

Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an imbalance causes mode collapse and reduces the diversity of synthesized…

Image Generation

Toward Tiny and High-quality Facial Makeup with Data Amplify Learning

2024-03-22 · Qiaoqiao Jin, Xuanhong Chen, Meiguang Jin, Ying Chen 외

Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet they grapple with the challenges of inaccurate supervision (e.g., face misalignment) and sophisticated facial prompts (including face par…

Face Parsing

SA-DiffuSeq: Addressing Computational and Scalability Challenges in Long-Document Generation with Sparse Attention

2025-12-23 · Alexandros Christoforos, Chadbourne Davis arxiv

Diffusion based approaches to long form text generation suffer from prohibitive computational cost and memory overhead as sequence length increases. We introduce SA-DiffuSeq, a diffusion framework that integrates sparse …

Code GenerationText Generation

Score Distillation via Reparametrized DDIM

2024-05-24 · Artem Lukoianov, Haitz Sáez de Ocáriz Borde, Kristjan Greenewald, Vitor Campagnolo Guizilini 외

While 2D diffusion models generate realistic, high-detail images, 3D shape generation methods like Score Distillation Sampling (SDS) built on these 2D diffusion models produce cartoon-like, over-smoothed shapes. To help …

3D Generation3D Shape GenerationDenoising