# Implicit Background Estimation for Semantic Segmentation

Source: [Implicit Background Estimation for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa65dc1e209131cea0ce32>)

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

Data updated: 2025-10-25T21:37:37.790Z

Authors: Charles Lehman, Dogancan Temel, Ghassan AlRegib

Published: 2019-05-23T09:20:52.000Z

## Abstract

Scene understanding and semantic segmentation are at the core of many computer vision tasks, many of which, involve interacting with humans in potentially dangerous ways. It is therefore paramount that techniques for principled design of robust models be developed. In this paper, we provide analytic and empirical evidence that correcting potentially errant non-distinct mappings that result from the softmax function can result in improving robustness characteristics on a state-of-the-art semantic segmentation model with minimal impact to performance and minimal changes to the code base.

## 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/1905.13306>)

[PDF](<https://arxiv.org/pdf/1905.13306.pdf>)