Papers › SNIPER: Efficient Multi-Scale Training

SNIPER: Efficient Multi-Scale Training

23 May 2018NeurIPS 2018 12arXiv:1805.09300archive 2025-07-28

Bharat Singh, Mahyar Najibi, Larry S. Davis

We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale. For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule. Hence, the number of chips generated per image during training adaptively changes based on the scene complexity. SNIPER only processes 30% more pixels compared to the commonly used single scale training at 800x1333 pixels on the COCO dataset. But, it also observes samples from extreme resolutions of the image pyramid, like 1400x2000 pixels. As SNIPER operates on resampled low resolution chips (512x512 pixels), it can have a batch size as large as 20 on a single GPU even with a ResNet-101 backbone. Therefore it can benefit from batch-normalization during training without the need for synchronizing batch-normalization statistics across GPUs. SNIPER brings training of instance level recognition tasks like object detection closer to the protocol for image classification and suggests that the commonly accepted guideline that it is important to train on high resolution images for instance level visual recognition tasks might not be correct. Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47.6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU. Code is available at https://github.com/MahyarNajibi/SNIPER/.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

MahyarNajibi/SNIPER officialmentioned in papermentioned on GitHubmxnetNOASSERTIONSyntology: not harvested report
Hwang64/PSIS mentioned on GitHubSyntology: not harvested report
starimpact/arm_SNIPER mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object DetectionRegion Proposalimage-classificationobject-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 SNIPER (ResNet-101) AP50 67.0 #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-101) AP75 51.6 #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-101) APL 58.1 #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-101) APM 48.9 #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-101) APS 29.6 #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-101) Hardware Burden 29G #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-101) box mAP 46.1 #129 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) AP50 65.0 #157 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) AP75 48.6 #157 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) APL 56.0 #157 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) APM 46.3 #157 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) APS 26.1 #157 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) Hardware Burden 29G #157 of 225 Archive leaderboard report
Object Detection COCO test-dev SNIPER (ResNet-50) box mAP 43.5 #157 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: SNIPER

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFaster R-CNNGlobal Average PoolingKaiming InitializationMax PoolingRPNReLUResidual BlockResidual ConnectionRoIPoolSNIPERSoftmaxWeight Decay

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