Superpixel-based Refinement for Object Proposal Generation

TL;DR

This paper introduces a superpixel-based refinement method that enhances object proposal segmentation accuracy by improving boundary adherence, building on the AttentionMask system.

Contribution

It presents a novel superpixel pooling and classification approach that significantly improves segmentation boundary accuracy in object proposal systems.

Findings

Up to 26.0% improvement in average recall

Significant boundary adherence improvements

Enhanced segmentation quality in qualitative and quantitative analyses

Abstract

Precise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation. Deep learning-based systems usually generate segmentations of objects based on coarse feature maps, due to the inherent downsampling in CNNs. This leads to segmentation boundaries not adhering well to the object boundaries in the image. To tackle this problem, we introduce a new superpixel-based refinement approach on top of the state-of-the-art object proposal system AttentionMask. The refinement utilizes superpixel pooling for feature extraction and a novel superpixel classifier to determine if a high precision superpixel belongs to an object or not. Our experiments show an improvement of up to 26.0% in terms of average recall compared to original AttentionMask. Furthermore, qualitative and quantitative analyses of the segmentations reveal significant improvements in terms of boundary adherence for the proposed refinement compared to various deep learning-based state-of-the-art object proposal generation systems.