Learning Dense Convolutional Embeddings for Semantic Segmentation

Abstract : This paper proposes a new deep convolutional neural network (DCNN) architecture that learns pixel embeddings, such that pairwise distances between the embeddings can be used to infer whether or not the pixels lie on the same region. That is, for any two pixels on the same object, the embeddings are trained to be similar; for any pair that straddles an object boundary, the embeddings are trained to be dissimilar. Experimental results show that when this embedding network is used in conjunction with a DCNN trained on semantic segmentation, there is a systematic improvement in per-pixel classification accuracy. Our contributions are integrated in the popular Caffe deep learning framework, and consist in straightforward modifications to convolution routines. As such, they can be exploited for any task involving convolution layers.
Type de document :
Pré-publication, Document de travail
2015
Liste complète des métadonnées

https://hal.inria.fr/hal-01263620
Contributeur : Iasonas Kokkinos <>
Soumis le : mercredi 27 janvier 2016 - 22:12:11
Dernière modification le : mardi 17 avril 2018 - 09:08:00

Lien texte intégral

Identifiants

  • HAL Id : hal-01263620, version 1
  • ARXIV : 1511.04377

Citation

Harley Adam, Iasonas Kokkinos, Kostas Derpanis. Learning Dense Convolutional Embeddings for Semantic Segmentation . 2015. 〈hal-01263620〉

Partager

Métriques

Consultations de la notice

225