Learning to Refine Object Segments

03/29/2016
by   Pedro O. Pinheiro, et al.
0

Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode object-level knowledge but are invariant to factors such as pose and appearance. In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach. The resulting bottom-up/top-down architecture is capable of efficiently generating high-fidelity object masks. Similarly to skip connections, our approach leverages features at all layers of the net. Unlike skip connections, our approach does not attempt to output independent predictions at each layer. Instead, we first output a coarse `mask encoding' in a feedforward pass, then refine this mask encoding in a top-down pass utilizing features at successively lower layers. The approach is simple, fast, and effective. Building on the recent DeepMask network for generating object proposals, we show accuracy improvements of 10-20 optimizing the overall network architecture, our approach, which we call SharpMask, is 50 image).

READ FULL TEXT

page 2

page 5

page 10

page 16

page 17

research
12/20/2016

Beyond Skip Connections: Top-Down Modulation for Object Detection

In recent years, we have seen tremendous progress in the field of object...
research
02/04/2020

Selective Segmentation Networks Using Top-Down Attention

Convolutional neural networks model the transformation of the input sens...
research
05/12/2017

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

We develop a novel deep contour detection algorithm with a top-down full...
research
05/08/2018

Learning Short-Cut Connections for Object Counting

Object counting is an important task in computer vision due to its growi...
research
08/02/2021

Projective Skip-Connections for Segmentation Along a Subset of Dimensions in Retinal OCT

In medical imaging, there are clinically relevant segmentation tasks whe...
research
03/03/2020

DDU-Nets: Distributed Dense Model for 3D MRI Brain Tumor Segmentation

Segmentation of brain tumors and their subregions remains a challenging ...

Please sign up or login with your details

Forgot password? Click here to reset