Learning multiple visual domains with residual adapters

05/22/2017
by   Sylvestre-Alvise Rebuffi, et al.
0

There is a growing interest in learning data representations that work well for many different types of problems and data. In this paper, we look in particular at the task of learning a single visual representation that can be successfully utilized in the analysis of very different types of images, from dog breeds to stop signs and digits. Inspired by recent work on learning networks that predict the parameters of another, we develop a tunable deep network architecture that, by means of adapter residual modules, can be steered on the fly to diverse visual domains. Our method achieves a high degree of parameter sharing while maintaining or even improving the accuracy of domain-specific representations. We also introduce the Visual Decathlon Challenge, a benchmark that evaluates the ability of representations to capture simultaneously ten very different visual domains and measures their ability to recognize well uniformly.

READ FULL TEXT
research
04/06/2022

Universal Representations: A Unified Look at Multiple Task and Domain Learning

We propose a unified look at jointly learning multiple vision tasks and ...
research
02/03/2019

Depthwise Convolution is All You Need for Learning Multiple Visual Domains

There is a growing interest in designing models that can deal with image...
research
02/26/2020

Disentangling Image Distortions in Deep Feature Space

Previous literature suggests that perceptual similarity is an emergent p...
research
09/28/2018

Domain Generalization with Domain-Specific Aggregation Modules

Visual recognition systems are meant to work in the real world. For this...
research
11/21/2017

Residual Parameter Transfer for Deep Domain Adaptation

The goal of Deep Domain Adaptation is to make it possible to use Deep Ne...
research
03/27/2018

Efficient parametrization of multi-domain deep neural networks

A practical limitation of deep neural networks is their high degree of s...
research
05/30/2017

Joint auto-encoders: a flexible multi-task learning framework

The incorporation of prior knowledge into learning is essential in achie...

Please sign up or login with your details

Forgot password? Click here to reset