Staying in Shape: Learning Invariant Shape Representations using Contrastive Learning

07/08/2021
by   Jeffrey Gu, et al.
0

Creating representations of shapes that are invari-ant to isometric or almost-isometric transforma-tions has long been an area of interest in shape anal-ysis, since enforcing invariance allows the learningof more effective and robust shape representations.Most existing invariant shape representations arehandcrafted, and previous work on learning shaperepresentations do not focus on producing invariantrepresentations. To solve the problem of learningunsupervised invariant shape representations, weuse contrastive learning, which produces discrimi-native representations through learning invarianceto user-specified data augmentations. To producerepresentations that are specifically isometry andalmost-isometry invariant, we propose new dataaugmentations that randomly sample these transfor-mations. We show experimentally that our methodoutperforms previous unsupervised learning ap-proaches in both effectiveness and robustness.

READ FULL TEXT
research
06/26/2020

Unsupervised Discovery of Object Landmarks via Contrastive Learning

Given a collection of images, humans are able to discover landmarks of t...
research
02/16/2021

Learning Invariant Representations using Inverse Contrastive Loss

Learning invariant representations is a critical first step in a number ...
research
04/15/2022

Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning

An ideal learned representation should display transferability and robus...
research
01/19/2022

TriCoLo: Trimodal Contrastive Loss for Fine-grained Text to Shape Retrieval

Recent work on contrastive losses for learning joint embeddings over mul...
research
01/29/2023

The Influences of Color and Shape Features in Visual Contrastive Learning

In the field of visual representation learning, performance of contrasti...
research
03/21/2022

A Contrastive Objective for Learning Disentangled Representations

Learning representations of images that are invariant to sensitive or un...
research
02/27/2023

Invariant Representations of Embedded Simplicial Complexes

Analyzing embedded simplicial complexes, such as triangular meshes and g...

Please sign up or login with your details

Forgot password? Click here to reset