Learning Finer-class Networks for Universal Representations

10/04/2018
by   Julien Girard, et al.
4

Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on a large annotated source-task onto a target-task of interest. This raises the question of how well the original representation is "universal", that is to say directly adapted to many different target-tasks. To improve such universality, the state-of-the-art consists in training networks on a diversified source problem, that is modified either by adding generic or specific categories to the initial set of categories. In this vein, we proposed a method that exploits finer-classes than the most specific ones existing, for which no annotation is available. We rely on unsupervised learning and a bottom-up split and merge strategy. We show that our method learns more universal representations than state-of-the-art, leading to significantly better results on 10 target-tasks from multiple domains, using several network architectures, either alone or combined with networks learned at a coarser semantic level.

READ FULL TEXT

page 3

page 5

page 9

page 10

page 11

page 15

page 16

research
12/27/2017

Learning More Universal Representations for Transfer-Learning

Transfer learning is commonly used to address the problem of the prohibi...
research
02/18/2020

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

The dominant object detection approaches treat each dataset separately a...
research
11/17/2019

Unsupervised Visual Representation Learning with Increasing Object Shape Bias

(Very early draft)Traditional supervised learning keeps pushing convolut...
research
03/20/2020

Selecting Relevant Features from a Universal Representation for Few-shot Classification

Popular approaches for few-shot classification consist of first learning...
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
05/25/2017

Deep image representations using caption generators

Deep learning exploits large volumes of labeled data to learn powerful m...

Please sign up or login with your details

Forgot password? Click here to reset