# Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions

Source: [Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions](<https://www.sota2.com/research/paper/68fa68c51e209131cea1e45d>)

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

Data updated: 2025-10-25T22:45:52.748Z

Authors: Hao Chen, Chunhua Shen, Zhi Tian

Published: 2020-11-19T12:42:10.000Z

## Abstract

Recently, fully-convolutional one-stage networks have shown superior performance comparing to two-stage frameworks for instance segmentation as typically they can generate higher-quality mask predictions with less computation. In addition, their simple design opens up new opportunities for joint multi-task learning. In this paper, we demonstrate that adding a single classification layer for semantic segmentation, fully-convolutional instance segmentation networks can achieve state-of-the-art panoptic segmentation quality. This is made possible by our novel dynamic rank-1 convolution (DR1Conv), a novel dynamic module that can efficiently merge high-level context information with low-level detailed features which is beneficial for both semantic and instance segmentation. Importantly, the proposed new method, termed DR1Mask, can perform panoptic segmentation by adding a single layer. To our knowledge, DR1Mask is the first panoptic segmentation framework that exploits a shared feature map for both instance and semantic segmentation by considering both efficacy and efficiency. Not only our framework is much more efficient -- twice as fast as previous best two-branch approaches, but also the unified framework opens up opportunities for using the same context module to improve the performance for both tasks. As a byproduct, when performing instance segmentation alone, DR1Mask is 10% faster and 1 point in mAP more accurate than previous state-of-the-art instance segmentation network BlendMask. Code is available at: https://git.io/AdelaiDet

## 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/2011.09796>)

[PDF](<https://arxiv.org/pdf/2011.09796.pdf>)