Learning to Segment Object Candidates
Pedro O. Pinheiro · Ronan Collobert · Piotr Dollar

Wed Dec 9th 11:35 AM -- 12:00 PM @ Room 210 A

Recent object detection systems rely on two critical steps: (1) a set of object proposals is predicted as efficiently as possible, and (2) this set of candidate proposals is then passed to an object classifier. Such approaches have been shown they can be fast, while achieving the state of the art in detection performance. In this paper, we propose a new way to generate object proposals, introducing an approach based on a discriminative convolutional network. Our model is trained jointly with two objectives: given an image patch, the first part of the system outputs a class-agnostic segmentation mask, while the second part of the system outputs the likelihood of the patch being centered on a full object. At test time, the model is efficiently applied on the whole test image and generates a set of segmentation masks, each of them being assigned with a corresponding object likelihood score. We show that our model yields significant improvements over state-of-the-art object proposal algorithms. In particular, compared to previous approaches, our model obtains substantially higher object recall using fewer proposals. We also show that our model is able to generalize to unseen categories it has not seen during training. Unlike all previous approaches for generating object masks, we do not rely on edges, superpixels, or any other form of low-level segmentation.

Author Information

Pedro O. Pinheiro (EPFL / Idiap)
Ronan Collobert (Facebook)

Ronan Collobert received his master degree in pure mathematics from University of Rennes (France) in 2000. He then performed graduate studies in University of Montreal and IDIAP (Switzerland) under the Bengio brothers, and received his PhD in 2004 from University of Paris VI. He joined NEC Labs (USA) in January 2005 as a postdoc, and became a research staff member after about one year. His research interests always focused on large-scale machine-learning algorithms, with a particular interest in semi-supervised learning and deep learning architectures. Two years ago, his research shifted in the natural language processing area, slowly going towards automatic text understanding.

Piotr Dollar (Facebook AI Research)

More from the Same Authors