paper-with-me

홈 › Papers

Self-supervised Pretraining of Visual Features in the Wild

2021-03-02 · Priya Goyal, Mathilde Caron, Benjamin Lefaudeux, Min Xu, Pengchao Wang, Vivek Pai, Mannat Singh, Vitaliy Liptchinsky, Ishan Misra, Armand Joulin, Piotr Bojanowski

Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods. These results have been achieved in a control environment, that is the highly curated ImageNet dataset. However, the premise of self-supervised learning is that it can learn from any random image and from any unbounded dataset. In this work, we explore if self-supervision lives to its expectation by training large models on random, uncurated images with no supervision. Our final SElf-supERvised (SEER) model, a RegNetY with 1.3B parameters trained on 1B random images with 512 GPUs achieves 84.2% top-1 accuracy, surpassing the best self-supervised pretrained model by 1% and confirming that self-supervised learning works in a real world setting. Interestingly, we also observe that self-supervised models are good few-shot learners achieving 77.9% top-1 with access to only 10% of ImageNet. Code: https://github.com/facebookresearch/vissl

📄 PDF Abstract BibTeX arXiv:2103.01988

Code (1)

facebookresearch/vissl 공식 구현 pytorch

Tasks

Image ClassificationSelf-Supervised Image ClassificationSelf-Supervised LearningSemi-Supervised Image Classification

Methods 이 논문이 사용한 방법론

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
SEER 설명 없음
Gradient Checkpointing Gradient Checkpointing is a method used for reducing the memory footprint when training deep neural networks, at the cost of having a small increase in computation time.
BYOL 설명 없음
Residual Connection 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Kaiming Initialization 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Self-supervised learning improves robustness of deep learning lung tumor segmentation to CT imaging differences

2024-05-14 · Jue Jiang, Aneesh Rangnekar, Harini Veeraraghavan

Self-supervised learning (SSL) is an approach to extract useful feature representations from unlabeled data, and enable fine-tuning on downstream tasks with limited labeled examples. Self-pretraining is a SSL approach th…

Computed Tomography (CT)Medical Image AnalysisSelf-Supervised LearningTumor Segmentation

Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition

2023-09-21 · Shuai Wang, Qibing Bai, Qi Liu, Jianwei Yu 외

Current speaker recognition systems primarily rely on supervised approaches, constrained by the scale of labeled datasets. To boost the system performance, researchers leverage large pretrained models such as WavLM to tr…

Speaker Recognition

Efficient Visual Pretraining with Contrastive Detection

2021-03-19 · ICCV 2021 10 · Olivier J. Hénaff, Skanda Koppula, Jean-Baptiste Alayrac, Aaron van den Oord 외

Self-supervised pretraining has been shown to yield powerful representations for transfer learning. These performance gains come at a large computational cost however, with state-of-the-art methods requiring an order of …

Semantic SegmentationTransfer Learning

Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings

2025-07-03 · Mufhumudzi Muthivhi, Terence L. van Zyl arxiv

Wildlife re-identification aims to match individuals of the same species across different observations. Current state-of-the-art (SOTA) models rely on class labels to train supervised models for individual classification…

Self-Supervised LearningTransfer Learning

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations

2024-01-08 · Helen Qu, Sang Michael Xie

Models trained on a labeled source domain (e.g., labeled images from wildlife camera traps) often generalize poorly when deployed on an out-of-distribution (OOD) target domain (e.g., images from new camera trap locations…

Contrastive LearningDomain AdaptationTime SeriesTime Series Classification