paper-with-me

Papers

Exploring Simple Siamese Representation Learning

2020-11-20 · CVPR 2021 1 · Xinlei Chen, Kaiming He

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing. We provide a hypothesis on the implication of stop-gradient, and further show proof-of-concept experiments verifying it. Our "SimSiam" method achieves competitive results on ImageNet and downstream tasks. We hope this simple baseline will motivate people to rethink the roles of Siamese architectures for unsupervised representation learning. Code will be made available.

📄 PDF Abstract BibTeX arXiv:2011.10566

Code (26)

facebookresearch/simsiam 공식 구현 pytorch
FloCF/SSL_pytorch pytorch
IgorSusmelj/simsiam-cifar10 pytorch
Mixture-of-Rookie/PASSL paddle
PaddlePaddle/PASSL paddle
PaperCodeReview/SimSiam-TF tf
PatrickHua/SimSiam pytorch
Reza-Safdari/SimSiam pytorch
SaeedShurrab/SimSiam-pytorch pytorch
Westlake-AI/openmixup pytorch
a07458666/simsiamfacenet pytorch
ahmdtaha/simsiam pytorch
amro-kamal/SimSiam-Implementation pytorch
facebookresearch/clip-rocket pytorch
juneweng/byol-pytorch pytorch
krishnatarun/ssl_dgc pytorch
leaderj1001/SimSiam pytorch
lightly-ai/lightly pytorch
miszkur/SelfSupervisedLearning tf
nikheelpandey/SimSiam-PyTorch pytorch
open-mmlab/mmselfsup pytorch
reza-safdari/simsiam-91.9-top1-acc-on-cifar10 pytorch
sayakpaul/SimSiam-TF tf
szq0214/S2-BNN pytorch
taoyang1122/pytorch-SimSiam pytorch
vturrisi/solo-learn pytorch

Tasks

Representation LearningSelf-Supervised Image Classification

Similar Papers 제목 키워드 기반

Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays

2023-01-30 · Rogier van der Sluijs, Nandita Bhaskhar, Daniel Rubin, Curtis Langlotz 외

Image augmentations are quintessential for effective visual representation learning across self-supervised learning techniques. While augmentation strategies for natural imaging have been studied extensively, medical ima…

Anomaly DetectionRepresentation LearningSelf-Supervised Learning

SiamJEPA: On the Role of Siamese Student Encoders in JEPA

2026-07-04 · Makoto Yamada hf

Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning…

Representation Learning

Content-based Representations of audio using Siamese neural networks

2018-02-15 · Manocha Pranay, Badlani Rohan, Kumar Anurag, Shah Ankit 외

In this paper, we focus on the problem of content-based retrieval for audio, which aims to retrieve all semantically similar audio recordings for a given audio clip query. This problem is similar to the problem of query …

Retrieval

Evaluation of Siamese Networks for Semantic Code Search

2020-10-12 · Raunak Sinha, Utkarsh Desai, Srikanth Tamilselvam, Senthil Mani

With the increase in the number of open repositories and discussion forums, the use of natural language for semantic code search has become increasingly common. The accuracy of the results returned by such systems, howev…

Code Search

Unlabeled Disentangling of GANs with Guided Siamese Networks

2019-05-01 · ICLR 2019 5 · Gökhan Yildirim, Nikolay Jetchev, Urs Bergmann

Disentangling underlying generative factors of a data distribution is important for interpretability and generalizable representations. In this paper, we introduce two novel disentangling methods. Our first method, Unla…