SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_28502 · AAAI · 2024

Spatial Transform Decoupling for Oriented Object Detection

Yunjie Tian, Hongtian Yu, Qixiang Ye, Yunfan Liu

Open in the Atlas

Code that ran

7 of 13 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 3 have no contract verdict; 3 failures of our instrument; 6 no recorded run), measured 2026-11-22; 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/aaai_28502.json · badge: /api/ran/aaai_28502.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
yuhongtian17/Spatial-Transform-Decoupling canonical (classifier label)
classifier basis: census
7 ran · 6 no recorded run
FunctionStatusWhere it lives
drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/models/vision_transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("55120f2026b56aa2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from gladzhang/Xformer, and GitHub detected no licence in that repository 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.

get_hivit_layer_id Ran
ran on a synthesized input
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/mmcv_custom/layer_decay_optimizer_constructor_hivit.py
code served (permissive licence) · get_code("7de3127f21102c10")
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 uses:
# - name: a string that may start with 'backbone.'
# - num_layers: an integer
# - main_block: a list-like object that supports .index() method

# Create a simple list for main_block
main_block = [0, 1, 2, 3, 4]

# Test case 1: name with 'backbone.' prefix and block index
name = "backbone.blocks.2.weight"
num_layers = 12

ARGS = {
    "name": name,
    "num_layers": num_layers,
    "main_block": main_block
}
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
get_num_layer_for_mae Ran
ran on a synthesized input
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/mmcv_custom/layer_decay_optimizer_constructor_backbone_frozen.py
code served (permissive licence) · get_code("9442eb59f6d0a7aa")
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

torch.manual_seed(0)

# Analyze the function:
# - var_name: string parameter used for startswith() and in() checks, and split operations
# - num_encoder_layers: int parameter used in arithmetic
# - num_decoder_layers: int parameter (appears in signature but not used in function body)
# - num_max_layer: int parameter used in arithmetic

# Test cases for var_name parameter:
test_cases = [
    'backbone.cls_token',
    'backbone.mask_token',
    'backbone.pos_embed',
    'backbone.patch_embed.something',
    'backbone.blocks.0.weight',
    'backbone.blocks.5.bias',
    'roi_head.bbox_head.norm.layer',
    'roi_head.bbox_head.decoder_embed.weight',
    'roi_head.bbox_head.decoder_blocks.2.conv',
    'roi_head.bbox_head.det_token',
    'some.other.parameter',
]

# Choose representative test values
var_name = 'backbone.blocks.3.weight'
num_encoder_layers = 12
num_decoder_layers = 8
num_max_layer = 24

ARGS = {
    'var_name': var_name,
    'num_encoder_layers': num_encoder_layers,
    'num_decoder_layers': num_decoder_layers,
    '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
get_num_layer_for_vit Ran
ran, honoured the contract we drafted
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/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
obb2poly_np Ran
ran on a synthesized input
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/utils/my_visualize.py
code served (permissive licence) · get_code("5037878f6a9f8aa1")
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 ndarray, ndim 2, dtype family float, shape (2, 8) 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 numpy as np

# Construct a valid oriented bounding box array
# Shape: (batch_size, 5) where each row is [x_ctr, y_ctr, w, h, angle]
obboxes = np.array([
    [10.0, 20.0, 4.0, 6.0, 0.785],  # center at (10,20), width=4, height=6, angle=0.785 rad
    [30.0, 40.0, 8.0, 5.0, 1.57],   # center at (30,40), width=8, height=5, angle=1.57 rad
], dtype=np.float32)

ARGS = {
    'obboxes': obboxes
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 8) — shape (2, 8) 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
parse_gt Ran
ran; our contract draft was wrong, not the code
yuhongtian17/Spatial-Transform-Decoupling/DOTA_devkit-master/dota_evaluation_task1.py
pointer only (licence: MIT); the stored copy get_code serves, from CAPTAIN-WHU/DOTA_devkit, is pointer only (licence: NONE) · get_code("0f59174083876439")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from CAPTAIN-WHU/DOTA_devkit, and GitHub detected no licence in that repository 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.

voc_ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yuhongtian17/Spatial-Transform-Decoupling/DOTA_devkit-master/dota_evaluation_task1.py
pointer only (licence: MIT); the stored copy get_code serves, from SupreethN/Hand-CNN, is pointer only (licence: NOASSERTION) · get_code("95c31c78be42f723")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from SupreethN/Hand-CNN, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

draw_rbboxes Not yet run
unverified (harvested, no recorded run)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/utils/my_image.py
code served (permissive licence) · get_code("9432da2297676e37")
How it ran

no invocation recorded.

visualize_boxes Not yet run
unverified (harvested, no recorded run)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/utils/my_visualize.py
code served (permissive licence) · get_code("f505399254eeae73")
How it ran

no invocation recorded.

visualize_boxes Not yet run
unverified (harvested, no recorded run)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/utils/visualize.py
code served (permissive licence) · get_code("014d68b7eac35e29")
How it ran

no invocation recorded.

visualize_boxes_and_labels_on_image_array Not yet run
unverified (harvested, no recorded run)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/utils/visualize.py
code served (permissive licence) · get_code("6f410b8889503829")
How it ran

no invocation recorded.

vit_small Not yet run
unverified (harvested, no recorded run)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/models/vision_transformer.py
code served (permissive licence) · get_code("a8f99539dbbaa617")
How it ran

no invocation recorded.

vit_tiny Not yet run
unverified (harvested, no recorded run)
yuhongtian17/Spatial-Transform-Decoupling/mmrotate-main/models/vision_transformer.py
code served (permissive licence) · get_code("1b5e2f11314f237d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
drop_path 224 other papers
146 dated earlier, 23 later, 54 same year, order not determinable, 1 undated · 38 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
and 221 more not named here
voc_ap 27 other papers
23 dated earlier, 3 later, 1 same year, order not determinable
1506.01497 (2015-06)
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1605.06409 (2016-05)
R-FCN: Object Detection via Region-based Fully Convolutional Networks
1609.03605 (2016-09)
Detecting Text in Natural Image with Connectionist Text Proposal Network
and 24 more not named here
get_num_layer_for_vit 5 other papers
5 dated earlier
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
parse_gt 2 other papers
2 dated earlier
1711.10398 (2017-11)
DOTA: A Large-scale Dataset for Object Detection in Aerial Images
1812.00155 (2018-12)
Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
draw_rbboxes 1 other paper
1 dated earlier
2212.07784 (2022-12)
RTMDet: An Empirical Study of Designing Real-Time Object Detectors
get_num_layer_for_mae 1 other paper
1 dated earlier
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
vit_small 1 other paper
1 dated earlier
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
vit_tiny 1 other paper
1 dated earlier
2007.09384 (2020-07)
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

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

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of spatial invariance in the data-forwarding process. In this study, we present a novel approach, termed Spatial Transform Decoupling (STD), providing a simple-yeteffective solution for oriented object detection with ViTs. Built upon stacked ViT blocks, STD utilizes separate network branches to predict the position, size, and angle of bounding boxes, effectively harnessing the spatial transform potential of ViTs in a divide-and-conquer fashion. Moreover, by aggregating cascaded activation masks (CAMs) computed upon the regressed parameters, STD gradually enhances features within regions of interest (RoIs), which complements the self-attention mechanism. Without bells and whistles, STD achieves state-of-the-art performance on the benchmark datasets including DOTA-v1.0 (82.24% mAP) and HRSC2016 (98.55% mAP), which demonstrates the effectiveness of the proposed method. Source code is available at https://github.com/yuhongtian17/Spatial-Transform-Decoupling.

For agents

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

get_harvested_code_for_paper("aaai_28502")
get_code_for_paper("aaai_28502")
have("aaai_28502")

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

curl https://syntology.ai/api/ran/aaai_28502.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_28502.svg)](https://syntology.ai/paper/aaai_28502)

Connect an agent — have() is free.