Log In Sign Up

Learning to Segment Object Candidates

by   Pedro O. Pinheiro, et al.

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.


page 3

page 5

page 6

page 10


DeepFH Segmentations for Superpixel-based Object Proposal Refinement

Class-agnostic object proposal generation is an important first step in ...

3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation

We present 3D-MPA, a method for instance segmentation on 3D point clouds...

Learning to Track Any Object

Object tracking can be formulated as "finding the right object in a vide...

What leads to generalization of object proposals?

Object proposal generation is often the first step in many detection mod...

Dynamic Proposals for Efficient Object Detection

Object detection is a basic computer vision task to loccalize and catego...

ContrastMask: Contrastive Learning to Segment Every Thing

Partially-supervised instance segmentation is a task which requests segm...

Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections

In interactive object segmentation a user collaborates with a computer v...

Code Repositories


Torch implementation of DeepMask and SharpMask

view repo


Deep Neural Network for object segmentation.

view repo


Torch implementation of DeepMask and SharpMask

view repo


A Keras implementation of DeepMask based on NIPS 2015 paper "Learning to Segment Object Candidates"

view repo


Torch implementation of DeepMask and SharpMask

view repo