Instance Search via Instance Level Segmentation and Feature Representation

TL;DR

This paper introduces an instance-level feature representation for search tasks, utilizing fully convolutional instance segmentation and deformable ResNeXt blocks to improve distinctiveness and scalability.

Contribution

It proposes a novel feature representation based on instance segmentation and deformable ResNeXt, enhancing instance search performance and segmentation accuracy.

Findings

Superior search performance on a custom dataset

Enhanced instance segmentation accuracy

Effective handling of various instance sizes and layouts

Abstract

Instance search is an interesting task as well as a challenging issue due to the lack of effective feature representation. In this paper, an instance level feature representation built upon fully convolutional instance-aware segmentation is proposed. The feature is ROI-pooled from the segmented instance region. So that instances in various sizes and layouts are represented by deep features in uniform length. This representation is further enhanced by the use of deformable ResNeXt blocks. Superior performance is observed in terms of its distinctiveness and scalability on a challenging evaluation dataset built by ourselves. In addition, the proposed enhancement on the network structure also shows superior performance on the instance segmentation task.