SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.18253 · ICLR · 2024

Workshop for Machine Learning for Remote Sensing (ML4RS) EFFICIENT REMOTE SENSING WITH HARMONIZED TRANSFER LEARNING AND MODALITY ALIGNMENT

Tengjun Huang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 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 0 have no contract verdict; 1 failure of our instrument; 5 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/2404.18253.json · badge: /api/ran/2404.18253.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
seekerhuang/harma marked official in Papers with Code
Papers with Code archive
1 ran · 5 no recorded run
FunctionStatusWhere it lives
read_json Ran
ran; our contract draft was wrong, not the code
seekerhuang/harma/models/model_retrieval.py
code served (permissive licence) · get_code("e1cf6464da33ec0c")
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) and returned dict. 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 json
import tempfile
import os

# Create a temporary JSON file with valid content
temp_dir = tempfile.mkdtemp()
temp_json_path = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(temp_json_path, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "rpath": temp_json_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
AllGather Not yet run
unverified (harvested, no recorded run)
seekerhuang/harma/models/model_retrieval.py
code served (permissive licence) · get_code("3d8d0c7edd3e4998")
How it ran

no invocation recorded.

HarMA Not yet run
unverified (harvested, no recorded run)
seekerhuang/harma/models/model_retrieval.py
code served (permissive licence) · get_code("b98dc0a1fd4cd372")
How it ran

no invocation recorded.

HarMABase Not yet run
unverified (harvested, no recorded run)
seekerhuang/harma/models/model_retrieval.py
code served (permissive licence) · get_code("71b3b1acfac0847d")
How it ran

no invocation recorded.

interpolate_relative_pos_embed Not yet run
unverified (harvested, no recorded run)
seekerhuang/harma/models/model_retrieval.py
code served (permissive licence) · get_code("bc9c8b1db97a5749")
How it ran

no invocation recorded.

load_pretrained_harma Not yet run
unverified (harvested, no recorded run)
seekerhuang/harma/models/model_retrieval.py
code served (permissive licence) · get_code("a0d20fab53560545")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
interpolate_relative_pos_embed
brick of this paper's assembly: helper
6 other papers
1 dated earlier, 5 later
2306.02898 (2023-06)
Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark
2409.19961 (2024-09)
Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval
2411.11919 (2024-11)
VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation
and 3 more not named here
read_json
brick of this paper's assembly: helper
2 other papers
2 later
2412.03017 (2024-12)
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach
Yang_Beyond_Walking_A_Large-Scale_Image-Text_Benchmark_for_Text-based_Person_Anomaly_ICCV_2025_paper (2025 (year only))
Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search

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

With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by finetuning. Although this paradigm has demonstrated potential in various multimodal downstream tasks, its implementation in the remote sensing domain encounters some obstacles. Specifically, the tendency for same-modality embeddings to cluster together impedes efficient transfer learning. To tackle this issue, we review the aim of multimodal transfer learning for downstream tasks from a unified perspective, and rethink the optimization process based on three distinct objectives. We propose "Harmonized Transfer Learning and Modality Alignment (HarMA)", a method that simultaneously satisfies task constraints, modality alignment, and single-modality uniform alignment, while minimizing training overhead through parameter-efficient fine-tuning. Remarkably, without the need for external data for training, HarMA achieves state-of-the-art performance in two popular multimodal retrieval tasks in the field of remote sensing. Our experiments reveal that HarMA achieves competitive and even superior performance to fully fine-tuned models with only minimal adjustable parameters. Due to its simplicity, HarMA can be integrated into almost all existing multimodal pretraining models. We hope this method can facilitate the efficient application of large models to a wide range of downstream tasks while significantly reducing the resource consumption 1 .

For agents

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

get_harvested_code_for_paper("2404.18253")
get_code_for_paper("2404.18253")
have("2404.18253")

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

curl https://syntology.ai/api/ran/2404.18253.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.18253.svg)](https://syntology.ai/paper/2404.18253)

Connect an agent — have() is free.