# Bridging Category-level and Instance-level Semantic Image Segmentation

Source: [Bridging Category-level and Instance-level Semantic Image Segmentation](<https://www.sota2.com/research/paper/68fa627c1e209131ce9f97ea>)

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

Data updated: 2026-01-04T02:50:39.553Z

Authors: Zifeng Wu, Chunhua Shen, Anton van den Hengel

Published: 2016-05-23T03:43:00.000Z

## Abstract

We propose an approach to instance-level image segmentation that is built on top of category-level segmentation. Specifically, for each pixel in a semantic category mask, its corresponding instance bounding box is predicted using a deep fully convolutional regression network. Thus it follows a different pipeline to the popular detect-then-segment approaches that first predict instances' bounding boxes, which are the current state-of-the-art in instance segmentation. We show that, by leveraging the strength of our state-of-the-art semantic segmentation models, the proposed method can achieve comparable or even better results to detect-then-segment approaches. We make the following contributions. (i) First, we propose a simple yet effective approach to semantic instance segmentation. (ii) Second, we propose an online bootstrapping method during training, which is critically important for achieving good performance for both semantic category segmentation and instance-level segmentation. (iii) As the performance of semantic category segmentation has a significant impact on the instance-level segmentation, which is the second step of our approach, we train fully convolutional residual networks to achieve the best semantic category segmentation accuracy. On the PASCAL VOC 2012 dataset, we obtain the currently best mean intersection-over-union score of 79.1%. (iv) We also achieve state-of-the-art results for instance-level segmentation.

## 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.

- [Semantic Segmentation on PASCAL-Context 60 classes (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-60-classes-test.md>): Semantic segmentation; PASCAL-Context 60 classes (test); mIoU: 44.5.

- [Instance Segmentation on PASCAL VOC 2012 (val)](<https://www.sota2.com/research/sota/instance-segmentation-on-pascal-voc-2012-val.md>): Instance Segmentation; PASCAL VOC 2012 (val); mAP @0.5: 61.5.

- [Semantic Segmentation on PASCAL-Context 59 classes (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-59-classes-test.md>): Semantic segmentation; PASCAL-Context 59 classes (test); mIoU: 44.5.

- [Semantic Segmentation on PASCAL Context (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-val.md>): Semantic segmentation; PASCAL Context (val); mIoU: 44.5.

- [Semantic Segmentation on PASCAL VOC 2012 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-test.md>): Semantic segmentation; PASCAL VOC 2012 (test); mIoU: 79.1.

- [Semantic Segmentation on Pascal Context (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-test.md>): Semantic segmentation; Pascal Context (test); mIoU: 44.5.

- [Semantic Segmentation on PASCAL VOC 2012 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-2012-val.md>): Semantic segmentation; PASCAL VOC 2012 (val); Mean IoU: 74.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1605.06885>)

[PDF](<https://arxiv.org/pdf/1605.06885.pdf>)

[Implementation](<http://host.robots.ox.ac.uk:8080/anonymous/MZVIPW.html>)
