SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting downstream performance. To overcome this limitation, we propose SASSL: Style Augmentations for Self Supervised Learning, a novel data augmentation technique based on Neural Style Transfer. SASSL decouples semantic and stylistic attributes in images and applies transformations exclusively to their style while preserving content, generating diverse samples that better retain semantic information. SASSL boosts top-1 image classification accuracy on ImageNet by up to 2 percentage points compared to established self-supervised methods like MoCo, SimCLR, and BYOL, while achieving superior transfer learning performance across various datasets. Because SASSL can be performed asynchronously as part of the data augmentation pipeline, these performance impacts can be obtained with no change in pretraining throughput.
Code (0)
등록된 구현이 없습니다.
Tasks
Data Augmentationimage-classificationImage ClassificationSelf-Supervised LearningStyle TransferTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Stain-Adaptive Self-Supervised Learning for Histopathology Image Analysis
It is commonly recognized that color variations caused by differences in stains is a critical issue for histopathology image analysis. Existing methods adopt color matching, stain separation, stain transfer or the combin…
Self-Supervised LearningSpeech-to-Speech Translation with Discrete-Unit-Based Style Transfer
Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy, but is unable to preserve the speaker timbre of the source speech. Meanwhile, the scarcity of hig…
In-Context LearningLanguage ModelingLanguage ModellingSpeech-to-Speech Translation+2Exploiting Social Media Content for Self-Supervised Style Transfer
Recent research on style transfer takes inspiration from unsupervised neural machine translation (UNMT), learning from large amounts of non-parallel data by exploiting cycle consistency loss, back-translation, and denois…
AttributeDenoisingMachine TranslationNMT+2StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis
The expressive quality of synthesized speech for audiobooks is limited by generalized model architecture and unbalanced style distribution in the training data. To address these issues, in this paper, we propose a self-s…
DecoderSpeech SynthesisSemantic Style Transfer for Enhancing Animal Facial Landmark Detection
Neural Style Transfer (NST) is a technique for applying the visual characteristics of one image onto another while preserving structural content. Traditionally used for artistic transformations, NST has recently been ada…
Data AugmentationDomain AdaptationFacial Landmark DetectionStyle Transfer