DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition
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.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection
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 GenerationContrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model
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 GenerationToward Tiny and High-quality Facial Makeup with Data Amplify Learning
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 ParsingSA-DiffuSeq: Addressing Computational and Scalability Challenges in Long-Document Generation with Sparse Attention
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 GenerationScore Distillation via Reparametrized DDIM
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