# Herding Generalizes Diverse M -Best Solutions

Source: [Herding Generalizes Diverse M -Best Solutions](<https://www.sota2.com/research/paper/68fa63171e209131ce9fca1c>)

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

Data updated: 2025-10-25T20:32:19.733Z

Authors: Ece Ozkan, Gemma Roig, Orcun Goksel, Xavier Boix

Published: 2016-11-14T12:13:58.000Z

## Abstract

We show that the algorithm to extract diverse M -solutions from a Conditional Random Field (called divMbest \[1\]) takes exactly the form of a Herding procedure \[2\], i.e. a deterministic dynamical system that produces a sequence of hypotheses that respect a set of observed moment constraints. This generalization enables us to invoke properties of Herding that show that divMbest enforces implausible constraints which may yield wrong assumptions for some problem settings. Our experiments in semantic segmentation demonstrate that seeing divMbest as an instance of Herding leads to better alternatives for the implausible constraints of divMbest.

## 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/1611.04353>)

[PDF](<https://arxiv.org/pdf/1611.04353.pdf>)