SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13376 · 2020

NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

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

Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will potentially lead to a lower recall rate and a higher threshold introduces more false positives. This problem is more severe in pedestrian detection because the instance density varies more intensively. However, previous works on NMS don't consider or vaguely consider the factor of the existent of nearby pedestrians. Thus, we propose Nearby Objects Hallucinator (NOH), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with NOH-NMS, which dynamically eases the suppression for the space that might contain other objects with a high likelihood. Compared to Greedy-NMS, our method, as the state-of-the-art, improves by $3.9\%$ AP, $5.1\%$ Recall, and $0.8\%$ $\text{MR}^{-2}$ on CrowdHuman to $89.0\%$ AP and $92.9\%$ Recall, and $43.9\%$ $\text{MR}^{-2}$ respectively.

For agents

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

get_harvested_code_for_paper("2007.13376")
get_code_for_paper("2007.13376")
have("2007.13376")

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

curl https://syntology.ai/api/ran/2007.13376.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13376.svg)](https://syntology.ai/paper/2007.13376)

Connect an agent — have() is free.