Disassembling Object Representations without Labels

04/03/2020
by   Zunlei Feng, et al.
0

In this paper, we study a new representation-learning task, which we termed as disassembling object representations. Given an image featuring multiple objects, the goal of disassembling is to acquire a latent representation, of which each part corresponds to one category of objects. Disassembling thus finds its application in a wide domain such as image editing and few- or zero-shot learning, as it enables category-specific modularity in the learned representations. To this end, we propose an unsupervised approach to achieving disassembling, named Unsupervised Disassembling Object Representation (UDOR). UDOR follows a double auto-encoder architecture, in which a fuzzy classification and an object-removing operation are imposed. The fuzzy classification constrains each part of the latent representation to encode features of up to one object category, while the object-removing, combined with a generative adversarial network, enforces the modularity of the representations and integrity of the reconstructed image. Furthermore, we devise two metrics to respectively measure the modularity of disassembled representations and the visual integrity of reconstructed images. Experimental results demonstrate that the proposed UDOR, despited unsupervised, achieves truly encouraging results on par with those of supervised methods.

READ FULL TEXT

page 10

page 12

page 14

research
12/31/2021

iCaps: Iterative Category-level Object Pose and Shape Estimation

This paper proposes a category-level 6D object pose and shape estimation...
research
03/08/2019

Auto-Encoding Progressive Generative Adversarial Networks For 3D Multi Object Scenes

3D multi object generative models allow us to synthesize a large range o...
research
06/01/2021

Supervised Speech Representation Learning for Parkinson's Disease Classification

Recently proposed automatic pathological speech classification technique...
research
04/05/2021

Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) targets recognizing new categories...
research
05/10/2018

Unsupervised Deep Representations for Learning Audience Facial Behaviors

In this paper, we present an unsupervised learning approach for analyzin...
research
11/03/2021

Dual Progressive Prototype Network for Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) aims to recognize new categories w...
research
11/05/2020

Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games

In visual guessing games, a Guesser has to identify a target object in a...

Please sign up or login with your details

Forgot password? Click here to reset