SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.04507 · CVPR · 2021

OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

Zhi Tang, Tingting Liang, Yongtao Wang, Haibin Ling, Guosheng Hu

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

Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy. Specifically, we first introduce six heterogeneous information paths to build our search space, namely top-down, bottom-up, fusingsplitting, scale-equalizing, skip-connect and none. Second, we propose a novel search space of FPNs, in which each FPN candidate is represented by a densely-connected directed acyclic graph (each node is a feature pyramid and each edge is one of the six heterogeneous information paths). Third, we propose an efficient one-shot search method to find the optimal path aggregation architecture; specifically, we first train a super-net and then find the optimal candidate with an evolutionary algorithm. Experimental results demonstrate the efficacy of the proposed OPANAS for object detection: (1) OPANAS is more efficient than state-of-the-art methods (e.g., NAS-FPN and Auto-FPN) at significantly smaller searching cost (e.g., only 4 GPU days on MS-COCO); (2) the optimal architecture found by OPANAS significantly improves main-stream detectors including RetinaNet, Faster R-CNN and Cascade R-CNN, by 2.3∼3.2 % mAP compared to their FPN counterparts;and (3) a new state-of-the-art accuracy-speed tradeoff (52.2 % mAP at 7.6 FPS) is achieved at smaller training costs than comparable recent arts. Code will be released at https://github.com/VDIGPKU/OPANAS.

For agents

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

get_harvested_code_for_paper("2103.04507")
get_code_for_paper("2103.04507")
have("2103.04507")

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

curl https://syntology.ai/api/ran/2103.04507.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.04507.svg)](https://syntology.ai/paper/2103.04507)

Connect an agent — have() is free.