SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.08192 · 2023

PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Images

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures 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/2312.08192.json · badge: /api/ran/2312.08192.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
casiatao/pad canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_num_layer_for_vit Ran
ran, honoured the contract we drafted
casiatao/pad/segmentation/mmcv_custom/layer_decay_optimizer_constructor.py
code served (permissive licence) · get_code("24385f6e21ea88d7")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import torch.nn as nn

torch.manual_seed(0)

# The function takes two parameters:
# 1. var_name: a string representing a variable name
# 2. num_max_layer: an integer representing the maximum number of layers

# Looking at the function body:
# - var_name is compared against strings and used with string operations like startswith() and split()
# - num_max_layer is used as an integer for arithmetic

# We'll test with a realistic var_name from a Vision Transformer backbone
var_name = "backbone.blocks.5.attn.qkv.weight"
num_max_layer = 12

ARGS = {
    "var_name": var_name,
    "num_max_layer": num_max_layer
}
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 int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
build_clip_model Not yet run
unverified (harvested, no recorded run)
casiatao/pad/pre-training/milan/clip_demo.py
code served (permissive licence) · get_code("c80ab71626411eeb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
get_num_layer_for_vit 5 other papers
2 dated earlier, 1 the same month, 1 later, 1 same year, order not determinable
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2212.04246 (2022-12)
ViTPose++: Vision Transformer for Generic Body Pose Estimation
and 2 more not named here

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

Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training dataset, 2) the distinctiveness of non-iconic infrared images rendering common pre-training tasks like masked image modeling (MIM) less effective, and 3) the scarcity of fine-grained textures making it particularly challenging to learn general image features. To address these issues, we construct a Multi-Scene Infrared Pre-training (MSIP) dataset comprising 178,756 images, and introduce object-sensitive random RoI cropping, an image preprocessing method, to tackle the challenge posed by non-iconic images. To alleviate the impact of weak textures on feature learning, we propose a pre-training paradigm called Pre-training with ADapter (PAD), which uses adapters to learn domain-specific features while freezing parameters pre-trained on ImageNet to retain the general feature extraction capability. This new paradigm is applicable to any transformer-based SSL method. Furthermore, to achieve more flexible coordination between pre-trained and newly-learned features in different layers and patches, a patchwise-scale adapter with dynamically learnable scale factors is introduced. Extensive experiments on three downstream tasks show that PAD, with only 1.23M pre-trainable parameters, outperforms other baseline paradigms including continual full pre-training on MSIP. Our code and dataset are available at https://github.com/casiatao/PAD.

For agents

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

get_harvested_code_for_paper("2312.08192")
get_code_for_paper("2312.08192")
have("2312.08192")

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

curl https://syntology.ai/api/ran/2312.08192.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.08192.svg)](https://syntology.ai/paper/2312.08192)

Connect an agent — have() is free.