SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.03188 · NeurIPS · 2021

Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach

Paul Swoboda, Ahmed Abbas

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a fully differentiable architecture for simultaneous semantic and instance segmentation (a.k.a. panoptic segmentation) consisting of a convolutional neural network and an asymmetric multiway cut problem solver. The latter solves a combinatorial optimization problem that elegantly incorporates semantic and boundary predictions to produce a panoptic labeling. Our formulation allows to directly maximize a smooth surrogate of the panoptic quality metric by backpropagating the gradient through the optimization problem. Experimental evaluation shows improvement by backpropagating through the optimization problem w.r.t. comparable approaches on Cityscapes and COCO datasets. Overall, our approach of combinatorial optimization for panoptic segmentation (COPS) shows the utility of using optimization in tandem with deep learning in a challenging large scale real-world problem and showcases benefits and insights into training such an architecture.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.03188")
get_code_for_paper("2106.03188")
have("2106.03188")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.03188.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.03188.svg)](https://syntology.ai/paper/2106.03188)

Connect an agent — have() is free.