LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity

04/06/2022
by   Tejan Karmali, et al.
3

In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection are based on learning dense (pixel-level) feature representations from an image, which are further used to learn landmarks in a semi-supervised manner. While there have been advances in self-supervised learning of image features for instance-level tasks like classification, these methods do not ensure dense equivariant representations. The property of equivariance is of interest for dense prediction tasks like landmark estimation. In this work, we introduce an approach to enhance the learning of dense equivariant representations in a self-supervised fashion. We follow a two-stage training approach: first, we train a network using the BYOL objective which operates at an instance level. The correspondences obtained through this network are further used to train a dense and compact representation of the image using a lightweight network. We show that having such a prior in the feature extractor helps in landmark detection, even under drastically limited number of annotations while also improving generalization across scale variations.

READ FULL TEXT

page 4

page 5

page 6

page 8

page 9

page 10

page 11

page 12

research
11/21/2021

HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning

Recently, self-supervised methods show remarkable achievements in image-...
research
06/10/2022

Exploring Feature Self-relation for Self-supervised Transformer

Learning representations with self-supervision for convolutional network...
research
03/22/2019

Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning

3D face reconstruction from a single 2D image is a challenging problem w...
research
10/01/2021

Self-supervised Secondary Landmark Detection via 3D Representation Learning

Recent technological developments have spurred great advances in the com...
research
08/03/2022

Character Generation through Self-Supervised Vectorization

The prevalent approach in self-supervised image generation is to operate...
research
11/30/2018

Improving Landmark Recognition using Saliency detection and Feature classification

Image Landmark Recognition has been one of the most sought-after classif...
research
03/15/2022

SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localization

Recent algorithms for image manipulation detection almost exclusively us...

Please sign up or login with your details

Forgot password? Click here to reset