Papers › MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations

MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations

18 Jun 2024arXiv:2406.12368archive 2025-07-28

Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni, Maziar Raissi

This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable Diffusion to replace an augmented instance of a real image, facilitating the learning of cross real-synthetic image representations. Our key insight is that while models trained solely on synthetic images underperform, combining real and synthetic data leads to more robust and adaptable representations. Experiments show MixDiff enhances SimCLR, BarlowTwins, and DINO across various robustness datasets and domain transfer tasks, boosting SimCLR's ImageNet-1K accuracy by 4.56%. Our framework also demonstrates comparable performance without needing any augmentations, a surprising finding in SSL where augmentations are typically crucial.

PaperPDFCode

Code

cryptonymous9/mixing-ssl officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionAverage PoolingColorJitterConvolutionDINODense ConnectionsDiffusionFeedforward NetworkGlobal Average PoolingKaiming InitializationLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionNT-XentRandom Gaussian BlurRandom Resized CropReLUResidual ConnectionSimCLRSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections