Methods › Computer Vision › Multi-Scale Training › SNIP

SNIP

17 papers tagged archive 2025-07-28

Introduced by Bharat Singh et al. in An Analysis of Scale Invariance in Object Detection - SNIP

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

SNIP, or Scale Normalization for Image Pyramids, is a multi-scale training scheme that selectively back-propagates the gradients of object instances of different sizes as a function of the image scale. SNIP is a modified version of MST where only the object instances that have a resolution close to the pre-training dataset, which is typically 224x224, are used for training the detector. In multi-scale training (MST), each image is observed at different resolutions therefore, at a high resolution (like 1400x2000) large objects are hard to classify and at a low resolution (like 480x800) small objects are hard to classify. Fortunately, each object instance appears at several different scales and some of those appearances fall in the desired scale range. In order to eliminate extreme scale objects, either too large or too small, training is only performed on objects that fall in the desired scale range and the remainder are simply ignored during back-propagation. Effectively, SNIP uses all the object instances during training, which helps capture all the variations in appearance and pose, while reducing the domain-shift in the scale-space for the pre-trained network.

PaperSource

In Syntology about another paper, arXiv:1810.02340: repository known, no verified implementation (declared_code; repositories: 5 listed of 8 in the graph, strongest link: official). About another paper: this answer is about arXiv:1810.02340, while the archive credits arXiv:1711.08189.

Origin paper of this answer, arXiv:1810.02340 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified (of 12 harvested samples) · 7 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 17 · with a code link: 7 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (4 of 17 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 17 of 17, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 21 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Network Pruning2
Object2
Object Detection2
object-detection2
All1
Benchmarking1
Contrastive Learning1
Equation Discovery1
Few-Shot Learning1
Image Classification1
Information Retrieval1
Math1
Mathematical Induction1
Mathematical Reasoning1
Memorization1
Model Compression1
Property Prediction1
Retrieval1
Sensitivity1
Symbolic Regression1

Usage over time archive 2025-07-28

Papers per year tagged with SNIP: 2017 to 2024, peak 6 6 0 2017: 1 paper 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 6 papers 2020 2021: 4 papers 2021 2022: 2 papers 2022 2023: 3 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (17 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Multi-Scale Training

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