paper-with-me

Papers

SEED: Self-supervised Distillation For Visual Representation

2021-01-12 · ICLR 2021 1 · Zhiyuan Fang, JianFeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang, Zicheng Liu

This paper is concerned with self-supervised learning for small models. The problem is motivated by our empirical studies that while the widely used contrastive self-supervised learning method has shown great progress on large model training, it does not work well for small models. To address this problem, we propose a new learning paradigm, named SElf-SupErvised Distillation (SEED), where we leverage a larger network (as Teacher) to transfer its representational knowledge into a smaller architecture (as Student) in a self-supervised fashion. Instead of directly learning from unlabeled data, we train a student encoder to mimic the similarity score distribution inferred by a teacher over a set of instances. We show that SEED dramatically boosts the performance of small networks on downstream tasks. Compared with self-supervised baselines, SEED improves the top-1 accuracy from 42.2% to 67.6% on EfficientNet-B0 and from 36.3% to 68.2% on MobileNet-v3-Large on the ImageNet-1k dataset.

📄 PDF Abstract BibTeX arXiv:2101.04731

Code (1)

jacobswan1/SEED 공식 구현 pytorch

Tasks

Knowledge DistillationSelf-Supervised LearningUnsupervised Pre-training

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…
InfoNCE 설명 없음
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
MoCo v2 MoCo v2 is an improved version of the Momentum Contrast self-supervised learning algorithm. Motivated by the findings presented in…

Similar Papers 제목 키워드 기반

Knowledge Distillation as Self-Supervised Learning

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

Self-supervised learning (SSL) methods have been shown to effectively train large neural networks with unlabeled data. These networks can produce useful image representations that can exceed the performance of supervised…

Knowledge DistillationSelf-Supervised Learning

TinySSL: Distilled Self-Supervised Pretraining for Sub-Megabyte MCU Models

2026-05-07 · Bibin Wilson arxiv

Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models with fewer than 500K parameters. We identify three obstacles at this …

Self-Supervised LearningRepresentation Learning

Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning

2023-04-13 · CVPR 2023 1 · Kaiyou Song, Jin Xie, Shan Zhang, Zimeng Luo

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small model…

Knowledge DistillationRepresentation LearningSelf-Supervised Learning

Distilling Visual Priors from Self-Supervised Learning

2020-08-01 · Bingchen Zhao, Xin Wen

Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ab…

ClassificationContrastive LearningGeneral Classificationimage-classification+3

Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization

2024-01-16 · Qi Bi, Wei Ji, Jingjun Yi, Haolan Zhan 외

High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g…

Fine-Grained Visual CategorizationKnowledge DistillationMultiple Instance LearningSelf-Supervised Learning