SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.12353 · 2019

Recursive Cascaded Networks for Unsupervised Medical Image Registration

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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 13 have no contract verdict; 0 failures of our instrument; 2 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/1907.12353.json · badge: /api/ran/1907.12353.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
microsoft/Recursive-Cascaded-Networks canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
w19787/Recursive-Cascaded-Networks-TF2.0 community (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
lajipeng/Recursive-Cascaded-Networks-master community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
LeakyReLU Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/utils.py
pointer only (licence: MIT) · get_code("c13693dd89acc8dc")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

ReLU Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/utils.py
pointer only (licence: MIT) · get_code("d3012985effa9042")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

convolve Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/utils.py
pointer only (licence: MIT) · get_code("236795484e1d97f3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

find_checkpoint_step Ran
ran on a synthesized input
lajipeng/Recursive-Cascaded-Networks-master/myeval.py
pointer only (licence: MIT) · get_code("c2500011559f51a1")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, lajipeng/Recursive-Cascaded-Networks-master, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_coef Ran
ran on a synthesized input
microsoft/Recursive-Cascaded-Networks/network/transform.py
code served (permissive licence) · get_code("d0de6300264407c3")
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 EagerTensor, ndim 3, dtype family float, shape (2, 4, 4) 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 tensorflow as tf

def get_coef(u):
    return tf.stack([(1 - u) ** 3 / 6, (3 * u ** 3 - 6 * u ** 2 + 4) / 6, (-3 * u ** 3 + 3 * u ** 2 + 3 * u + 1) / 6, u ** 3 / 6], axis=1)

# Create a small TensorFlow tensor as input
u = tf.constant([[0.0, 0.25, 0.5, 0.75],
                  [0.1, 0.3, 0.6, 0.9]], dtype=tf.float32)

ARGS = {
    "u": u
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 4) 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
mask_metrics Ran
ran on a synthesized input
microsoft/Recursive-Cascaded-Networks/network/recursive_cascaded_networks.py
code served (permissive licence) · get_code("aec35f503dcf8ea9")
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 tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tensorflow as tf
import numpy as np

# Create small segmentation masks
# batch_size=2, spatial_dims=4x3
batch_size = 2
height = 4
width = 3

# seg1: foreground values around 255, background around 0
seg1_values = np.array([
    [[255, 0, 255], [0, 255, 0], [255, 255, 0], [0, 0, 255]],
    [[255, 255, 0], [0, 0, 255], [255, 0, 255], [0, 255, 0]]
], dtype=np.uint8)
seg1 = tf.constant(seg1_values, dtype=tf.uint8)

# seg2: different foreground/background pattern
seg2_values = np.array([
    [[255, 255, 0], [255, 0, 255], [0, 255, 255], [255, 0, 0]],
    [[0, 255, 255], [255, 255, 0], [0, 255, 0], [255, 255, 255]]
], dtype=np.uint8)
seg2 = tf.constant(seg2_values, dtype=tf.uint8)

ARGS = {
    "seg1": seg1,
    "seg2": seg2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
mask_metrics Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/recursive_cascaded_networks.py
pointer only (licence: MIT) · get_code("64f8504da2d48138")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

masked_mean Ran
ran on a synthesized input
microsoft/Recursive-Cascaded-Networks/network/framework.py
code served (permissive licence) · get_code("d3971ed2df2141bf")
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 EagerTensor, ndim 0, dtype family float, 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 tensorflow as tf
import numpy as np

# Create small tensors for the masked_mean function
arr = tf.constant([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

mask = tf.constant([[1.0, 1.0, 0.0, 1.0],
                    [1.0, 0.0, 1.0, 1.0]], dtype=tf.float32)

ARGS = {
    "arr": arr,
    "mask": mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 0, dtype family float, 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
masked_mean Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/framework.py
pointer only (licence: MIT) · get_code("650bb46908cc826f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

pad_3d Ran
ran on a synthesized input
microsoft/Recursive-Cascaded-Networks/network/transform.py
code served (permissive licence) · get_code("d7569a1677102532")
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 EagerTensor, ndim 5, dtype family float, shape (2, 5, 6, 7, 1) 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 tensorflow as tf
import numpy as np

# Create a small 5D tensor for padding
# Shape: [batch=2, depth=3, height=4, width=5, channels=1]
mat = tf.constant(np.random.randn(2, 3, 4, 5, 1), dtype=tf.float32)

# Padding amount
pad = 1

ARGS = {
    "mat": mat,
    "pad": pad,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 5, dtype family float, shape (2, 5, 6, 7, 1) — shape (2, 5, 6, 7, 1) 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
pad_3d Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/transform.py
pointer only (licence: MIT) · get_code("ca28c9c65ab9db48")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

sample_power Ran
ran on a synthesized input
w19787/Recursive-Cascaded-Networks-TF2.0/network/transform.py
pointer only (licence: MIT) · get_code("4a403051bd61a1a2")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, w19787/Recursive-Cascaded-Networks-TF2.0, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

set_tf_keys Ran
ran on a synthesized input
microsoft/Recursive-Cascaded-Networks/network/framework.py
code served (permissive licence) · get_code("2cc4d063c1d1d0aa")
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 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 torch

torch.manual_seed(0)

# The function set_tf_keys takes:
# 1. feed_dict - a dictionary to process
# 2. **kwargs - additional keyword arguments to process
# Both are converted to have ':0' appended to keys and merged

feed_dict = {
    'input_tensor': torch.randn(2, 4),
    'output_tensor': torch.randn(2, 3),
}

kwargs_dict = {
    'weights': torch.randn(4, 3),
    'bias': torch.randn(3),
}

ARGS = {
    'feed_dict': feed_dict,
}
ARGS.update(kwargs_dict)
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 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
get_range Not yet run
unverified (harvested, no recorded run)
microsoft/Recursive-Cascaded-Networks/data_util/liver.py
code served (permissive licence) · get_code("3a4da2a87b9cc362")
How it ran

no invocation recorded.

sample_power Not yet run
unverified (harvested, no recorded run)
microsoft/Recursive-Cascaded-Networks/network/transform.py
code served (permissive licence) · get_code("d560d49c07951d0a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 7 later) and 8 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_coef 2 other papers
2 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network
aaai_25276 (2023 (year only))
Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation
masked_mean 2 other papers
2 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network
aaai_25276 (2023 (year only))
Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation
pad_3d 2 other papers
2 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network
aaai_25276 (2023 (year only))
Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation
sample_power 2 other papers
2 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network
aaai_25276 (2023 (year only))
Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation
set_tf_keys 2 other papers
2 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network
aaai_25276 (2023 (year only))
Robust One-Shot Segmentation of Brain Tissues via Image-Aligned Style Transformation
find_checkpoint_step 1 other paper
1 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network
get_range 1 other paper
1 later
1909.11966 (2019-09)
Dual-Stream Pyramid Registration Network

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

We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration. The proposed architecture is simple in design and can be built on any base network. The moving image is warped successively by each cascade and finally aligned to the fixed image; this procedure is recursive in a way that every cascade learns to perform a progressive deformation for the current warped image. The entire system is end-to-end and jointly trained in an unsupervised manner. In addition, enabled by the recursive architecture, one cascade can be iteratively applied for multiple times during testing, which approaches a better fit between each of the image pairs. We evaluate our method on 3D medical images, where deformable registration is most commonly applied. We demonstrate that recursive cascaded networks achieve consistent, significant gains and outperform state-of-the-art methods. The performance reveals an increasing trend as long as more cascades are trained, while the limit is not observed. Code is available at https://github.com/microsoft/Recursive-Cascaded-Networks.

For agents

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

get_harvested_code_for_paper("1907.12353")
get_code_for_paper("1907.12353")
have("1907.12353")

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

curl https://syntology.ai/api/ran/1907.12353.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.12353.svg)](https://syntology.ai/paper/1907.12353)

Connect an agent — have() is free.