A Relational Model for One-Shot Classification
Not on the map. Why?
Abstract (arXiv)
We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 8 Nov 2021.
Builds on
28 of 37 references.
References · 28
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2016Layer Normalizationcited by 5,579
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Matching Networks for One Shot Learningcited by 2,246
16 more
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2015Gated Graph Sequence Neural Networkscited by 792
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2017A simple neural network module for relational reasoningcited by 345
- 2017Few-Shot Learning with Graph Neural Networkscited by 324
- 2017A Neural Representation of Sketch Drawingscited by 311
- 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 202
- 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
- 2019The Omniglot challenge: a 3-year progress reportcited by 54
- 2019PARN: Position-Aware Relation Networks for Few-Shot Learningcited by 27
- 2020SketchEmbedNet: Learning Novel Concepts by Imitating Drawingscited by 18
- 2017Attentive Recurrent Comparatorscited by 13
Built on by
Not cited yet.