PatchNet: Unsupervised Object Discovery based on Patch Embedding

by   Hankyu Moon, et al.

We demonstrate that frequently appearing objects can be discovered by training randomly sampled patches from a small number of images (100 to 200) by self-supervision. Key to this approach is the pattern space, a latent space of patterns that represents all possible sub-images of the given image data. The distance structure in the pattern space captures the co-occurrence of patterns due to the frequent objects. The pattern space embedding is learned by minimizing the contrastive loss between randomly generated adjacent patches. To prevent the embedding from learning the background, we modulate the contrastive loss by color-based object saliency and background dissimilarity. The learned distance structure serves as object memory, and the frequent objects are simply discovered by clustering the pattern vectors from the random patches sampled for inference. Our image representation based on image patches naturally handles the position and scale invariance property that is crucial to multi-object discovery. The method has been proven surprisingly effective, and successfully applied to finding multiple human faces and bodies from natural images.



There are no comments yet.


page 2

page 7

page 9


Unsupervised Natural Image Patch Learning

Learning a metric of natural image patches is an important tool for anal...

StampNet: unsupervised multi-class object discovery

Unsupervised object discovery in images involves uncovering recurring pa...

Object-aware Contrastive Learning for Debiased Scene Representation

Contrastive self-supervised learning has shown impressive results in lea...

Self-supervisory Signals for Object Discovery and Detection

In robotic applications, we often face the challenge of discovering new ...

Mid-level Deep Pattern Mining

Mid-level visual element discovery aims to find clusters of image patche...

Saliency Detection with Spaces of Background-based Distribution

In this letter, an effective image saliency detection method is proposed...

Ensemble of Part Detectors for Simultaneous Classification and Localization

Part-based representation has been proven to be effective for a variety ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.