paper-with-me

Papers

SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer

2023-12-02 · Renan A. Rojas-Gomez, Karan Singhal, Ali Etemad, Alex Bijamov, Warren R. Morningstar, Philip Andrew Mansfield

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.

📄 PDF Abstract BibTeX arXiv:2312.01187

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationimage-classificationImage ClassificationSelf-Supervised LearningStyle TransferTransfer Learning

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Kaiming Initialization 설명 없음
Random Resized Crop 설명 없음
NT-Xent NT-Xent, or Normalized Temperature-scaled Cross Entropy Loss, is a loss function. Let $\text{sim}\left(\mathbf{u}, \mathbf{v}\right) =…

Similar Papers 제목 키워드 기반

Stain-Adaptive Self-Supervised Learning for Histopathology Image Analysis

2022-08-08 · Hai-Li Ye, Da-Han Wang

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 Learning

Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer

2023-09-14 · Yongqi Wang, Jionghao Bai, Rongjie Huang, RuiQi Li 외

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+2

Exploiting Social Media Content for Self-Supervised Style Transfer

2022-05-18 · NAACL (SocialNLP) 2022 7 · Dana Ruiter, Thomas Kleinbauer, Cristina España-Bonet, Josef van Genabith 외

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+2

StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis

2023-12-19 · Xueyuan Chen, Xi Wang, Shaofei Zhang, Lei He 외

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 Synthesis

Semantic Style Transfer for Enhancing Animal Facial Landmark Detection

2025-05-08 · Anadil Hussein, Anna Zamansky, George Martvel

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