Boosting Few-Shot Visual Learning with Self-Supervision

06/12/2019
by   Spyros Gidaris, et al.
0

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learning focuses instead on unlabeled data and looks into it for the supervisory signal to feed high capacity deep neural networks. In this work we exploit the complementarity of these two domains and propose an approach for improving few-shot learning through self-supervision. We use self-supervision as an auxiliary task in a few-shot learning pipeline, enabling feature extractors to learn richer and more transferable visual representations while still using few annotated samples. Through self-supervision, our approach can be naturally extended towards using diverse unlabeled data from other datasets in the few-shot setting. We report consistent improvements across an array of architectures, datasets and self-supervision techniques.

READ FULL TEXT
research
06/17/2019

Boosting Supervision with Self-Supervision for Few-shot Learning

We present a technique to improve the transferability of deep representa...
research
03/10/2021

Multi-Pretext Attention Network for Few-shot Learning with Self-supervision

Few-shot learning is an interesting and challenging study, which enables...
research
04/16/2021

Pareto Self-Supervised Training for Few-Shot Learning

While few-shot learning (FSL) aims for rapid generalization to new conce...
research
07/28/2019

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

Few-shot learning algorithms aim to learn model parameters capable of ad...
research
08/31/2023

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data

Few-shot keyword spotting (FS-KWS) models usually require large-scale an...
research
07/21/2020

Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification

While supervised techniques in re-identification are extremely effective...
research
09/28/2020

Sense and Learn: Self-Supervision for Omnipresent Sensors

Learning general-purpose representations from multisensor data produced ...

Please sign up or login with your details

Forgot password? Click here to reset