Dynamic Few-Shot Visual Learning without Forgetting

by   Spyros Gidaris, et al.

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research problem with many practical advantages on real world vision applications. In this context, the goal of our work is to devise a few-shot visual learning system that during test time it will be able to efficiently learn novel categories from only a few training data while at the same time it will not forget the initial categories on which it was trained (here called base categories). To achieve that goal we propose (a) to extend an object recognition system with an attention based few-shot classification weight generator, and (b) to redesign the classifier of a ConvNet model as the cosine similarity function between feature representations and classification weight vectors. The latter, apart from unifying the recognition of both novel and base categories, it also leads to feature representations that generalize better on "unseen" categories. We extensively evaluate our approach on Mini-ImageNet where we manage to improve the prior state-of-the-art on few-shot recognition (i.e., we achieve 56.20 respectively) while at the same time we do not sacrifice any accuracy on the base categories, which is a characteristic that most prior approaches lack. Finally, we apply our approach on the recently introduced few-shot benchmark of Bharath and Girshick [4] where we also achieve state-of-the-art results. The code and models of our paper will be published on: https://github.com/gidariss/FewShotWithoutForgetting


BaseTransformers: Attention over base data-points for One Shot Learning

Few shot classification aims to learn to recognize novel categories usin...

Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning

Given an initial recognition model already trained on a set of base clas...

A Study on Representation Transfer for Few-Shot Learning

Few-shot classification aims to learn to classify new object categories ...

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers

One of the most significant challenges facing a few-shot learning task i...

On the Importance of Firth Bias Reduction in Few-Shot Classification

Learning accurate classifiers for novel categories from very few example...

Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners

Few-shot recognition involves training an image classifier to distinguis...

ProFormer: Learning Data-efficient Representations of Body Movement with Prototype-based Feature Augmentation and Visual Transformers

Automatically understanding human behaviour allows household robots to i...

Please sign up or login with your details

Forgot password? Click here to reset