Methods › Computer Vision › Multi-Scale Training › SNIP
SNIP
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.
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.
-
DRIVE: Dual Gradient-Based Rapid Iterative Pruning 1 Apr 2024 · 0 repositories · arXiv:2404.03687
-
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks 30 Oct 2023 · 1 repository · arXiv:2310.19470Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
In defense of parameter sharing for model-compression 17 Oct 2023 · 0 repositories · arXiv:2310.11611
-
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training 3 Oct 2023 · 2 repositories · arXiv:2310.02227Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
Design of Discrete-time Matrix All-Pass Filters Using Subspace Nevanlinna Pick Interpolation 25 Oct 2022 · 0 repositories · arXiv:2210.14015
-
One-shot Network Pruning at Initialization with Discriminative Image Patches 13 Sep 2022 · 0 repositories · arXiv:2209.05683
-
Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity 5 Jul 2021 · 1 repository · arXiv:2107.02306Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples)
-
Why is Pruning at Initialization Immune to Reinitializing and Shuffling? 5 Jul 2021 · 0 repositories · arXiv:2107.01808
-
How are journals cited? characterizing journal citations by type of citation 22 Feb 2021 · 0 repositories · arXiv:2102.11043
-
Scale Normalized Image Pyramids with AutoFocus for Object Detection 10 Feb 2021 · 1 repository · arXiv:2102.05646
-
FreezeNet: Full Performance by Reduced Storage Costs 28 Nov 2020 · 0 repositories · arXiv:2011.14087
-
Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior 5 Oct 2020 · 1 repository · arXiv:2010.01791
-
Winning Lottery Tickets in Deep Generative Models 5 Oct 2020 · 1 repository · arXiv:2010.02350
-
Pruning Neural Networks at Initialization: Why are We Missing the Mark? 18 Sep 2020 · 0 repositories · arXiv:2009.08576
-
Data-dependent Pruning to find the Winning Lottery Ticket 25 Jun 2020 · 0 repositories · arXiv:2006.14350
-
Pruning via Iterative Ranking of Sensitivity Statistics 1 Jun 2020 · 1 repository · arXiv:2006.00896Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
An Analysis of Scale Invariance in Object Detection - SNIP 22 Nov 2017 · 0 repositories · arXiv:1711.08189
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.
Usage over time archive 2025-07-28
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
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