Skip to Main content Skip to Navigation
Conference papers

Pushing the boundaries of boundary detection using deep learning

Abstract : In this work we show that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection. Our contributions consist firstly in combining a careful design of the loss for boundary detection training, a multi-resolution architecture and training with external data to improve the detection accuracy of the current state of the art. When measured on the standard Berkeley Segmentation Dataset, we improve theopti-mal dataset scale F-measure from 0.780 to 0.808 - while human performance is at 0.803. We further improve performance to 0.813 by combining deep learning with grouping, integrating the Normalized Cuts technique within a deep network. We also examine the potential of our boundary detector in conjunction with the task of semantic segmentation and demonstrate clear improvements over state-of-the-art systems. Our detector is fully integrated in the popular Caffe framework and processes a 320x420 image in less than a second.
Document type :
Conference papers
Complete list of metadatas
Contributor : Kamilia Abdani <>
Submitted on : Wednesday, January 8, 2020 - 3:47:05 PM
Last modification on : Thursday, July 9, 2020 - 4:06:04 PM


  • HAL Id : hal-02432711, version 1


Iasonas Kokkinos. Pushing the boundaries of boundary detection using deep learning. 4th International Conference on Learning Representations, ICLR 2016, May 2016, San Juan, Puerto Rico. ⟨hal-02432711⟩



Record views