Papers › NAS-FCOS: Fast Neural Architecture Search for Object Detection

NAS-FCOS: Fast Neural Architecture Search for Object Detection

11 Jun 2019CVPR 2020 6arXiv:1906.04423archive 2025-07-28

Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang

The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal architectures, although typically such algorithms need an excessive amount of computational resources, e.g., a few thousand GPU-days. To date, on challenging vision tasks such as object detection, NAS, especially fast versions of NAS, is less studied. Here we propose to search for the decoder structure of object detectors with search efficiency being taken into consideration. To be more specific, we aim to efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS, using a tailored reinforcement learning paradigm. With carefully designed search space, search algorithms and strategies for evaluating network quality, we are able to efficiently search a top-performing detection architecture within 4 days using 8 V100 GPUs. The discovered architecture surpasses state-of-the-art object detection models (such as Faster R-CNN, RetinaNet and FCOS) by 1.5 to 3.5 points in AP on the COCO dataset, with comparable computation complexity and memory footprint, demonstrating the efficacy of the proposed NAS for object detection.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1906.04423")

Code

Syntology Ran 6 of 7 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: community (archive-listed): 7 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Lausannen/NAS-FCOS mentioned on GitHubpytorchBSD-2-Clause report
open-mmlab/mmdetection pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 6 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

6ran
1unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Lausannen/NAS-FCOS. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_params Lausannen/NAS-FCOS/maskrcnn_benchmark/nas/helpers/utils.py community (archive-listed) ran BSD-2-Clause (permissive) · 4b7b9c0a067a58b6 · report
conv1x1 Lausannen/NAS-FCOS/maskrcnn_benchmark/nas/modeling/layer_factory.py community (archive-listed) ran BSD-2-Clause (permissive) · 91a91c0edd5005d4 · report
conv3x3 Lausannen/NAS-FCOS/maskrcnn_benchmark/nas/modeling/layer_factory.py community (archive-listed) ran BSD-2-Clause (permissive) · 44528dc0396b98a2 · report
conv_bn Lausannen/NAS-FCOS/maskrcnn_benchmark/nas/modeling/layer_factory.py community (archive-listed) ran BSD-2-Clause (permissive) · cfd0138367178ace · report
deprocess_img Lausannen/NAS-FCOS/maskrcnn_benchmark/nas/helpers/utils.py community (archive-listed) ran BSD-2-Clause (permissive) · cf7a8fe1ae8b87b8 · report
load_ckpt Lausannen/NAS-FCOS/maskrcnn_benchmark/nas/helpers/utils.py community (archive-listed) ran BSD-2-Clause (permissive) · 2d70cc16e9c12926 · report
interpolate Lausannen/NAS-FCOS/maskrcnn_benchmark/layers/misc.py community (archive-listed) unverified BSD-2-Clause (permissive) · 2902bf4410253ff7 · report

Tasks

DecoderNeural Architecture SearchObjectObject DetectionReinforcement Learningobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev ResNeXt-64x4d-101 NAS-FCOS @128-256 w/improvements box mAP 46.1 #131 of 225 Archive leaderboard report
Object Detection COCO test-dev ResNet-50 NAS-FCOS @256 box mAP 39.8 #201 of 225 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: NAS-FCOS

1x1 ConvolutionConvolutionFCOSFPNFaster R-CNNFocal LossLSTMNAS-FCOSNon Maximum SuppressionRPNRetinaNetRoIPoolSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections