# Object Detection Free Instance Segmentation With Labeling Transformations

Source: [Object Detection Free Instance Segmentation With Labeling Transformations](<https://www.sota2.com/research/paper/68fa63031e209131ce9fc530>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:51:52.608Z

Authors: Long Jin, Zeyu Chen, Zhuowen Tu

Published: 2016-11-28T05:52:37.000Z

## Abstract

Instance segmentation has attracted recent attention in computer vision and existing methods in this domain mostly have an object detection stage. In this paper, we study the intrinsic challenge of the instance segmentation problem, the presence of a quotient space (swapping the labels of different instances leads to the same result), and propose new methods that are object proposal- and object detection- free. We propose three alternative methods, namely pixel-based affinity mapping, superpixel-based affinity learning, and boundary-based component segmentation, all focusing on performing labeling transformations to cope with the quotient space problem. By adopting fully convolutional neural networks (FCN) like models, our framework attains competitive results on both the PASCAL dataset (object-centric) and the Gland dataset (texture-centric), which the existing methods are not able to do. Our work also has the advantages in its transparency, simplicity, and being all segmentation based.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1611.08991>)

[PDF](<https://arxiv.org/pdf/1611.08991.pdf>)