Enabling the Network to Surf the Internet
Not on the map. Why?
Abstract (arXiv)
Few-shot learning is challenging due to the limited data and labels. Existing algorithms usually resolve this problem by pre-training the model with a considerable amount of annotated data which shares knowledge with the target domain. Nevertheless, large quantities of homogenous data samples are not always available. To tackle this issue, we develop a framework that enables the model to surf the Internet, which implies that the model can collect and annotate data without manual effort. Since the online data is virtually limitless and continues to be generated, the model can thus be empowered to constantly obtain up-to-date knowledge from the Internet. Additionally, we observe that the generalization ability of the learned representation is crucial for self-supervised learning. To present its importance, a naive yet efficient normalization strategy is proposed. Consequentially, this strategy boosts the accuracy of the model significantly (20.46% at most). We demonstrate the superiority of the proposed framework with experiments on miniImageNet, tieredImageNet and Omniglot. The results indicate that our method has surpassed previous unsupervised counterparts by a large margin (more than 10%) and obtained performance comparable with the supervised ones.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 64 references that are in the map. First posted on arXiv 24 Feb 2021.
Builds on
40 of 64 references.
References · 40
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2020Supervised Contrastive Learningcited by 2,803
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
28 more
- 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
- 2017Continual Learning with Deep Generative Replaycited by 1,152
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
- 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
- 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
- 2018Meta-learning with differentiable closed-form solverscited by 395
- 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
- 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2019Large Scale Adversarial Representation Learningcited by 238
- 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
- 2017Colorization as a Proxy Task for Visual Understandingcited by 175
- 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
- 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
- 2016A Deep Hierarchical Approach to Lifelong Learning in Minecraftcited by 90
- 2018Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizercited by 87
- 2018Unsupervised Learning via Meta-Learningcited by 81
- 2019Few-Shot Learning with Global Class Representationscited by 44
- 2020Self-supervised Knowledge Distillation for Few-shot Learningcited by 41
- 2017Weakly Supervised Semantic Segmentation using Web-Crawled Videoscited by 38
- 2019Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptationcited by 32
- 2019PARN: Position-Aware Relation Networks for Few-Shot Learningcited by 27
- 2019Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentationcited by 18
- 2020Are Fewer Labels Possible for Few-shot Learning?cited by 2
Built on by
Citing papers per year: 2021: 1; 2022: 1.
2 papers.