Instance Segmentation of Indoor Scenes using a Coverage Loss. Silberman, N., Sontag, D., & Fergus, R. In Fleet, D. J., Pajdla, T., Schiele, B., & Tuytelaars, T., editors, Proceedings of the 13th European Conference on Computer Vision (ECCV), volume 8689, of Lecture Notes in Computer Science, pages 616–631, 2014. Springer. Paper abstract bibtex A major limitation of existing models for semantic segmentation is the inability to identify individual instances of the same class: when labeling pixels with only semantic classes, a set of pixels with the same label could represent a single object or ten. In this work, we introduce a model to perform both semantic and instance segmentation simultaneously. We introduce a new higher-order loss function that directly minimizes the coverage metric and evaluate a variety of region features, including those from a convolutional network. We apply our model to the NYU Depth V2 dataset, obtaining state of the art results.
@inproceedings{SilSonFer_ECCV14,
author = {Nathan Silberman and David Sontag and Rob Fergus},
title = {Instance Segmentation of Indoor Scenes using a Coverage Loss},
booktitle = {Proceedings of the 13th European Conference on Computer Vision (ECCV)},
series = {Lecture Notes in Computer Science},
volume = {8689},
publisher = {Springer},
editor = {David J. Fleet and
Tom{\'{a}}s Pajdla and
Bernt Schiele and
Tinne Tuytelaars},
pages = {616--631},
year = {2014},
keywords = {Computer vision, Machine learning},
url_Paper = {http://people.csail.mit.edu/dsontag/papers/SilSonFer_ECCV14.pdf},
abstract = {A major limitation of existing models for semantic segmentation is the inability to identify individual instances of the same class: when labeling pixels with only semantic classes, a set of pixels with the same label could represent a single object or ten. In this work, we introduce a model to perform both semantic and instance segmentation simultaneously. We introduce a new higher-order loss function that directly minimizes the coverage metric and evaluate a variety of region features, including those from a convolutional network. We apply our model to the NYU Depth V2 dataset, obtaining state of the art results.}
}
Downloads: 0
{"_id":"F5HWstvjvf4oTLJST","bibbaseid":"silberman-sontag-fergus-instancesegmentationofindoorscenesusingacoverageloss-2014","author_short":["Silberman, N.","Sontag, D.","Fergus, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Nathan"],"propositions":[],"lastnames":["Silberman"],"suffixes":[]},{"firstnames":["David"],"propositions":[],"lastnames":["Sontag"],"suffixes":[]},{"firstnames":["Rob"],"propositions":[],"lastnames":["Fergus"],"suffixes":[]}],"title":"Instance Segmentation of Indoor Scenes using a Coverage Loss","booktitle":"Proceedings of the 13th European Conference on Computer Vision (ECCV)","series":"Lecture Notes in Computer Science","volume":"8689","publisher":"Springer","editor":[{"firstnames":["David","J."],"propositions":[],"lastnames":["Fleet"],"suffixes":[]},{"firstnames":["Tomás"],"propositions":[],"lastnames":["Pajdla"],"suffixes":[]},{"firstnames":["Bernt"],"propositions":[],"lastnames":["Schiele"],"suffixes":[]},{"firstnames":["Tinne"],"propositions":[],"lastnames":["Tuytelaars"],"suffixes":[]}],"pages":"616–631","year":"2014","keywords":"Computer vision, Machine learning","url_paper":"http://people.csail.mit.edu/dsontag/papers/SilSonFer_ECCV14.pdf","abstract":"A major limitation of existing models for semantic segmentation is the inability to identify individual instances of the same class: when labeling pixels with only semantic classes, a set of pixels with the same label could represent a single object or ten. In this work, we introduce a model to perform both semantic and instance segmentation simultaneously. We introduce a new higher-order loss function that directly minimizes the coverage metric and evaluate a variety of region features, including those from a convolutional network. We apply our model to the NYU Depth V2 dataset, obtaining state of the art results.","bibtex":"@inproceedings{SilSonFer_ECCV14,\n author = {Nathan Silberman and David Sontag and Rob Fergus},\n title = {Instance Segmentation of Indoor Scenes using a Coverage Loss},\n booktitle = {Proceedings of the 13th European Conference on Computer Vision (ECCV)},\n series = {Lecture Notes in Computer Science},\n volume = {8689},\n publisher = {Springer},\n editor = {David J. Fleet and\n Tom{\\'{a}}s Pajdla and\n Bernt Schiele and\n Tinne Tuytelaars},\n pages = {616--631},\n year = {2014},\n keywords = {Computer vision, Machine learning},\n url_Paper = {http://people.csail.mit.edu/dsontag/papers/SilSonFer_ECCV14.pdf},\n abstract = {A major limitation of existing models for semantic segmentation is the inability to identify individual instances of the same class: when labeling pixels with only semantic classes, a set of pixels with the same label could represent a single object or ten. In this work, we introduce a model to perform both semantic and instance segmentation simultaneously. We introduce a new higher-order loss function that directly minimizes the coverage metric and evaluate a variety of region features, including those from a convolutional network. We apply our model to the NYU Depth V2 dataset, obtaining state of the art results.}\n}\n\n","author_short":["Silberman, N.","Sontag, D.","Fergus, R."],"editor_short":["Fleet, D. J.","Pajdla, T.","Schiele, B.","Tuytelaars, T."],"key":"SilSonFer_ECCV14","id":"SilSonFer_ECCV14","bibbaseid":"silberman-sontag-fergus-instancesegmentationofindoorscenesusingacoverageloss-2014","role":"author","urls":{" paper":"http://people.csail.mit.edu/dsontag/papers/SilSonFer_ECCV14.pdf"},"keyword":["Computer vision","Machine learning"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"http://people.csail.mit.edu/dsontag/papers/bibtex/david_sontag_papers_all.bib","dataSources":["g3ofqhxNQWsRWkCrp"],"keywords":["computer vision","machine learning"],"search_terms":["instance","segmentation","indoor","scenes","using","coverage","loss","silberman","sontag","fergus"],"title":"Instance Segmentation of Indoor Scenes using a Coverage Loss","year":2014}