SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.06223 · NeurIPS · 2022

Latency-aware Spatial-wise Dynamic Networks

Gao Huang, Shiji Song, Yizeng Han, Zhihang Yuan, Yifan Pu, Chenhao Xue, Guangyu Sun

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2210.06223.json · badge: /api/ran/2210.06223.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
leaplabthu/lasnet community
Papers with Code archive
3 ran · 0 no recorded run
leaplabthu/laudnet community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
ExpandMask Ran
ran on a synthesized input · constructed an object; no result was computed
leaplabthu/lasnet/imagenet_classification/models/dyn_regnet.py
pointer only (licence: NONE) · get_code("8048294bd9458d33")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leaplabthu/lasnet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Masker Ran
ran on a synthesized input
leaplabthu/lasnet/imagenet_classification/models/dyn_regnet.py
pointer only (licence: NONE) · get_code("ea3b08aad6d4debc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leaplabthu/lasnet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Masker_spatial Ran
ran on a synthesized input · constructed an object; no result was computed
leaplabthu/laudnet/imagenet_classification/models/utils.py
pointer only (licence: NONE) · get_code("f18eaaece7f0ee12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leaplabthu/laudnet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv1x1 Ran
ran; our contract draft was wrong, not the code
leaplabthu/laudnet/imagenet_classification/models/utils.py
pointer only (licence: NONE) · get_code("a709d613d6c8ba15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leaplabthu/laudnet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv1x1 Ran
ran; our contract draft was wrong, not the code
leaplabthu/lasnet/imagenet_classification/models/dyn_regnet.py
pointer only (licence: NONE) · get_code("9208c344d230ce4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leaplabthu/lasnet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial redundancy in image features and saves a considerable amount of unnecessary computation. However, the theoretical efficiency achieved by previous methods can hardly translate into a realistic speedup, especially on the multi-core processors (e.g. GPUs). The key challenge is that the existing literature has only focused on designing algorithms with minimal computation, ignoring the fact that the practical latency can also be influenced by scheduling strategies and hardware properties. To bridge the gap between theoretical computation and practical efficiency, we propose a latency-aware spatial-wise dynamic network (LASNet), which performs coarse-grained spatially adaptive inference under the guidance of a novel latency prediction model. The latency prediction model can efficiently estimate the inference latency of dynamic networks by simultaneously considering algorithms, scheduling strategies, and hardware properties. We use the latency predictor to guide both the algorithm design and the scheduling optimization on various hardware platforms. Experiments on image classification, object detection and instance segmentation demonstrate that the proposed framework significantly improves the practical inference efficiency of deep networks. For example, the average latency of a ResNet-101 on the ImageNet validation set could be reduced by 36% and 46% on a server GPU (Nvidia Tesla-V100) and an edge device (Nvidia Jetson TX2 GPU) respectively without sacrificing the accuracy. Code is available at https://github.com/LeapLabTHU/LASNet.

For agents

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

get_harvested_code_for_paper("2210.06223")
get_code_for_paper("2210.06223")
have("2210.06223")

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

curl https://syntology.ai/api/ran/2210.06223.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.06223.svg)](https://syntology.ai/paper/2210.06223)

Connect an agent — have() is free.