SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.20087 · CVPR · 2025

OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

Yizhou Yu, Meng Lou

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 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/2502.20087.json · badge: /api/ran/2502.20087.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
lmmmeng/overlock canonical (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
get_bn Ran
ran; our contract draft was wrong, not the code
lmmmeng/overlock/models/overlock.py
code served (permissive licence) · get_code("d977b7ab30c244f2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned BatchNorm2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

ARGS = {
    "dim": 64,
    "use_sync_bn": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_conv2d Ran
ran on a synthesized input
lmmmeng/overlock/models/overlock.py
code served (permissive licence) · get_code("2a98f57fe1928cf6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn
from timm.models.layers import to_2tuple

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'kernel_size': 7,
    'stride': 1,
    'padding': None,
    'dilation': 1,
    'groups': 1,
    'bias': True,
    'attempt_use_lk_impl': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
depthwise_conv2d_implicit_gemm, timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
fuse_bn Not yet run
unverified (harvested, no recorded run)
lmmmeng/overlock/models/overlock.py
code served (permissive licence) · get_code("5a70ce114f24b052")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
fuse_bn 1 other paper
1 dated earlier
2311.15599 (2023-11)
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition
get_bn 1 other paper
1 dated earlier
2311.15599 (2023-11)
UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

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

Top-down attention plays a crucial role in the human vision system, wherein the brain initially obtains a rough overview of a scene to discover salient cues (i.e., overview first), followed by a more careful finer-grained examination (i.e., look closely next). However, modern ConvNets remain confined to a pyramid structure that successively downsamples the feature map for receptive field expansion, neglecting this crucial biomimetic principle. We present OverLoCK, the first pure ConvNet backbone architecture that explicitly incorporates a top-down attention mechanism. Unlike pyramid backbone networks, our design features a branched architecture with three synergistic subnetworks: 1) a Base-Net that encodes low/mid-level features; 2) a lightweight Overview-Net that generates dynamic top-down attention through coarse global context modeling (i.e., overview first); and 3) a robust Focus-Net that performs finer-grained perception guided by top-down attention (i.e., look closely next). To fully unleash the power of top-down attention, we further propose a novel context-mixing dynamic convolution (ContMix) that effectively models long-range dependencies while preserving inherent local inductive biases even when the input resolution increases, addressing critical limitations in existing convolutions. Our OverLoCK exhibits a notable performance improvement over existing methods. For instance, OverLoCK-T achieves a Top-1 accuracy of 84.2%, significantly surpassing ConvNeXt-B while using only around one-third of the FLOPs/parameters. On object detection, our OverLoCK-S clearly surpasses MogaNet-B by 1% in AP b . On semantic segmentation, our OverLoCK-T remarkably improves UniRepLKNet-T by 1.7% in mIoU. Code is publicly available at https://rb.gy/wit4jh.

For agents

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

get_harvested_code_for_paper("2502.20087")
get_code_for_paper("2502.20087")
have("2502.20087")

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

curl https://syntology.ai/api/ran/2502.20087.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.20087.svg)](https://syntology.ai/paper/2502.20087)

Connect an agent — have() is free.