REVIEW 5 cited by
DreamDA: Generative Data Augmentation with Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The acquisition of large-scale, high-quality data is a resource-intensive and time-consuming endeavor. Compared to conventional Data Augmentation (DA) techniques (e.g. cropping and rotation), exploiting prevailing diffusion models for data generation has received scant attention in classification tasks. Existing generative DA methods either inadequately bridge the domain gap between real-world and synthesized images, or inherently suffer from a lack of diversity. To solve these issues, this paper proposes a new classification-oriented framework DreamDA, which enables data synthesis and label generation by way of diffusion models. DreamDA generates diverse samples that adhere to the original data distribution by considering training images in the original data as seeds and perturbing their reverse diffusion process. In addition, since the labels of the generated data may not align with the labels of their corresponding seed images, we introduce a self-training paradigm for generating pseudo labels and training classifiers using the synthesized data. Extensive experiments across four tasks and five datasets demonstrate consistent improvements over strong baselines, revealing the efficacy of DreamDA in synthesizing high-quality and diverse images with accurate labels. Our code will be available at https://github.com/yunxiangfu2001/DreamDA.
Forward citations
Cited by 5 Pith papers
-
Layering Virtual Try-On
A two-stage diffusion pipeline and new benchmark let virtual try-on add, remove, or swap clothing layers while preserving inner layers, with SOTA results on the new LVTON benchmark and on VITON-HD/DressCode.
-
Decomposing Subject-Driven Image Generation via Intermediate Structural Prediction
A two-stage method predicts an intermediate Canny map for structure then renders the image conditioned on appearance and structure, paired with a 100k text-aware dataset, to improve detail preservation in subject-driv...
-
Reading a Ruler in the Wild
RulerNet detects centimeter marks on rulers in natural images and estimates pixel-per-centimeter scale via a learned geometric progression model, outperforming prior OCR-based and frequency-based baselines.
-
Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery
DiffGRE generates synthetic images through cross-image interpolation in diffusion and CLIP latent spaces, filters them for diversity, and uses pseudo-labels to improve on-the-fly fine-grained category discovery.
-
Canonical Latent Representations in Conditional Diffusion Models
Projecting out the top Jacobian singular directions in a conditional diffusion model's latent space yields class prototypes that, when used for distillation, improve classifier robustness and generalization.
Discussion (0). Sign in to comment.