SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.05074 · 2019

UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 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 3 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/1912.05074.json · badge: /api/ran/1912.05074.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
manuelhz/dissertation community (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 2 no recorded run
FunctionStatusWhere it lives
double_conv Ran
ran; our contract draft was wrong, not the code
manuelhz/dissertation/BraTS/BraTS_unet_training.py
pointer only (licence: MIT); the stored copy get_code serves, from EvgenyDyshlyuk/Oil_Seep_Detection, is pointer only (licence: NONE) · get_code("3e9ea4498e4b8a8d")
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 EvgenyDyshlyuk/Oil_Seep_Detection, 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.

double_conv2 Ran
ran on a synthesized input
manuelhz/dissertation/BraTS/BraTS_unet_++_training.py
code served (permissive licence) · get_code("be52c1e7e30a5f3b")
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 Sequential. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'in_ch': 3,
    'out_ch': 16,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
up3 Ran
ran on a synthesized input
manuelhz/dissertation/BraTS/BraTS_unet_++_training.py
code served (permissive licence) · get_code("a6667f374238aad5")
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 Tensor, ndim 2, dtype family float, shape (2, 12) 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)

# The function concatenates three tensors along dimension 1
# We need three tensors with the same batch size (dim 0) and compatible shapes for concatenation on dim 1
x1 = torch.randn(2, 3)
x2 = torch.randn(2, 4)
x3 = torch.randn(2, 5)

ARGS = {
    "x1": x1,
    "x2": x2,
    "x3": x3,
}
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 Tensor, ndim 2, dtype family float, shape (2, 12) — shape (2, 12) 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
up4 Ran
ran on a synthesized input
manuelhz/dissertation/BraTS/BraTS_unet_++_training.py
code served (permissive licence) · get_code("22a234a1173d001e")
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 Tensor, ndim 2, dtype family float, shape (2, 18) 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)

# Create four small tensors with batch size 2
# Each tensor has a different channel dimension to make shapes distinct
x1 = torch.randn(2, 3)  # batch=2, channels=3
x2 = torch.randn(2, 4)  # batch=2, channels=4
x3 = torch.randn(2, 5)  # batch=2, channels=5
x4 = torch.randn(2, 6)  # batch=2, channels=6

ARGS = {
    "x1": x1,
    "x2": x2,
    "x3": x3,
    "x4": x4,
}
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 Tensor, ndim 2, dtype family float, shape (2, 18) — shape (2, 18) 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
double_conv2 Not yet run
unverified (harvested, no recorded run)
manuelhz/dissertation/BraTS/BraTS_unet_++_pruned.py
code served (permissive licence) · get_code("d4f3d905e75200e3")
How it ran

no invocation recorded.

unetp Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from frgfm/Holocron
pointer only · get_code("6b0f999f9e74b1c8")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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. No invocation recorded.

unetpp Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from frgfm/Holocron
pointer only · get_code("42e3369990bb3769")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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. No invocation recorded.

up3 Not yet run
unverified (harvested, no recorded run)
manuelhz/dissertation/BraTS/BraTS_unet_++_pruned.py
code served (permissive licence) · get_code("7a968c1589ba71bb")
How it ran

no invocation recorded.

up4 Not yet run
unverified (harvested, no recorded run)
manuelhz/dissertation/BraTS/BraTS_unet_++_pruned.py
code served (permissive licence) · get_code("7488d0ba5adf5cd7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
double_conv 4 other papers
1 dated earlier, 3 later
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
2007.07843 (2020-07)
Few-shot Scene-adaptive Anomaly Detection
2404.06737 (2024-04)
Disguised Copyright Infringement of Latent Diffusion Models
and 1 more not named here
unetp 1 other paper
1 dated earlier
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
unetpp 1 other paper
1 dated earlier
1807.10165 (2018-07)
UNet++: A Nested U-Net Architecture for Medical Image Segmentation

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

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extensive architecture search or inefficient ensemble of models of varying depths; and (2) their skip connections impose an unnecessarily restrictive fusion scheme, forcing aggregation only at the same-scale feature maps of the encoder and decoder sub-networks. To overcome these two limitations, we propose UNet++, a new neural architecture for semantic and instance segmentation, by (1) alleviating the unknown network depth with an efficient ensemble of U-Nets of varying depths, which partially share an encoder and co-learn simultaneously using deep supervision; (2) redesigning skip connections to aggregate features of varying semantic scales at the decoder sub-networks, leading to a highly flexible feature fusion scheme; and (3) devising a pruning scheme to accelerate the inference speed of UNet++. We have evaluated UNet++ using six different medical image segmentation datasets, covering multiple imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and electron microscopy (EM), and demonstrating that (1) UNet++ consistently outperforms the baseline models for the task of semantic segmentation across different datasets and backbone architectures; (2) UNet++ enhances segmentation quality of varying-size objects -- an improvement over the fixed-depth U-Net; (3) Mask RCNN++ (Mask R-CNN with UNet++ design) outperforms the original Mask R-CNN for the task of instance segmentation; and (4) pruned UNet++ models achieve significant speedup while showing only modest performance degradation. Our implementation and pre-trained models are available at https://github.com/MrGiovanni/UNetPlusPlus.

For agents

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

get_harvested_code_for_paper("1912.05074")
get_code_for_paper("1912.05074")
have("1912.05074")

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

curl https://syntology.ai/api/ran/1912.05074.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.05074.svg)](https://syntology.ai/paper/1912.05074)

Connect an agent — have() is free.