Self-Supervised Contextual Bandits in Computer Vision

03/18/2020
by   Aniket Anand Deshmukh, et al.
0

Contextual bandits are a common problem faced by machine learning practitioners in domains as diverse as hypothesis testing to product recommendations. There have been a lot of approaches in exploiting rich data representations for contextual bandit problems with varying degree of success. Self-supervised learning is a promising approach to find rich data representations without explicit labels. In a typical self-supervised learning scheme, the primary task is defined by the problem objective (e.g. clustering, classification, embedding generation etc.) and the secondary task is defined by the self-supervision objective (e.g. rotation prediction, words in neighborhood, colorization, etc.). In the usual self-supervision, we learn implicit labels from the training data for a secondary task. However, in the contextual bandit setting, we don't have the advantage of getting implicit labels due to lack of data in the initial phase of learning. We provide a novel approach to tackle this issue by combining a contextual bandit objective with a self supervision objective. By augmenting contextual bandit learning with self-supervision we get a better cumulative reward. Our results on eight popular computer vision datasets show substantial gains in cumulative reward. We provide cases where the proposed scheme doesn't perform optimally and give alternative methods for better learning in these cases.

READ FULL TEXT
research
01/14/2023

Gated Self-supervised Learning For Improving Supervised Learning

In past research on self-supervised learning for image classification, t...
research
09/17/2020

Online Semi-Supervised Learning in Contextual Bandits with Episodic Reward

We considered a novel practical problem of online learning with episodic...
research
07/04/2018

TextTopicNet - Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces

The immense success of deep learning based methods in computer vision he...
research
12/23/2020

Self-supervised self-supervision by combining deep learning and probabilistic logic

Labeling training examples at scale is a perennial challenge in machine ...
research
03/29/2017

On Convergence Property of Implicit Self-paced Objective

Self-paced learning (SPL) is a new methodology that simulates the learni...
research
09/23/2017

Self-supervised learning: When is fusion of the primary and secondary sensor cue useful?

Self-supervised learning (SSL) is a reliable learning mechanism in which...

Please sign up or login with your details

Forgot password? Click here to reset