CVMar 29, 2016

Learning to Refine Object Segments

arXiv:1603.08695v2856 citations
Originality Incremental advance
AI Analysis

This work addresses the problem of efficient and accurate object segmentation for computer vision applications, presenting an incremental improvement over existing methods.

The paper tackles the challenge of object segmentation by proposing a top-down refinement approach that augments feedforward networks, resulting in a bottom-up/top-down architecture that generates high-fidelity object masks. It shows accuracy improvements of 10-20% in average recall and is 50% faster than the baseline DeepMask network.

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% in average recall for various setups. Additionally, by optimizing the overall network architecture, our approach, which we call SharpMask, is 50% faster than the original DeepMask network (under .8s per image).

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes