SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.04562 · ICCV · 2021

Deep Metric Learning for Open World Semantic Segmentation

Yu Wang, Ming Liu, Jun Peng, Yun Junhao, Cai Michael

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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 2 have no contract verdict; 2 failures 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/2108.04562.json · badge: /api/ran/2108.04562.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
Jun-CEN/Open-World-Semantic-Segmentation community (classifier label)
classifier basis not recorded on the link
5 ran · 5 no recorded run
FunctionStatusWhere it lives
Normalization Ran
ran on a synthesized input
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/main_distillation.py
code served (permissive licence) · get_code("345e436021e6eb22")
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, 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 numpy as np

# Construct a small numpy array for normalization
# Use distinct dimensions to make shapes unambiguous
x = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
])

ARGS = {
    "x": x
}
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, 4) — shape (2, 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
estimator Ran
ran on a synthesized input
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/Read_img.py
code served (permissive licence) · get_code("f661b8566492d18b")
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 (4, 3) 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 matplotlib
matplotlib.use('Agg')  # Use non-interactive backend to avoid display issues

torch.manual_seed(0)

# Create a small image tensor
# The function expects image.shape[0] and image.shape[1] to be accessible
# It passes the image to plt.imshow(), which expects a 2D or 3D array
# Create a small 4x3 grayscale image
image = torch.rand(4, 3)

ARGS = {
    "image": image
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, 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 (4, 3) — shape (4, 3) 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
fpr_and_fdr_at_recall Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Jun-CEN/Open-World-Semantic-Segmentation/anomaly/anom_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Wuyingwen/Pursuing-Feature-Separation-for-OOD-Detection, is pointer only (licence: NONE) · get_code("7242da839b9822be")
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 Wuyingwen/Pursuing-Feature-Separation-for-OOD-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.

get_measures Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Jun-CEN/Open-World-Semantic-Segmentation/anomaly/anom_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Wuyingwen/Pursuing-Feature-Separation-for-OOD-Detection, is pointer only (licence: NONE) · get_code("b9b6c36f7a3e7e67")
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 Wuyingwen/Pursuing-Feature-Separation-for-OOD-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.

stable_cumsum Ran
ran, honoured the contract we drafted
Jun-CEN/Open-World-Semantic-Segmentation/anomaly/anom_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from fanghenshaometeor/ood-kernel-pca-ext, is pointer only (licence: NONE) · get_code("d4acb3120a027622")
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 fanghenshaometeor/ood-kernel-pca-ext, 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.

Certainty Not yet run
unverified (harvested, no recorded run)
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/main_distillation.py
code served (permissive licence) · get_code("de2f19be459091e2")
How it ran

no invocation recorded.

convert_to_separable_conv Not yet run
unverified (harvested, no recorded run)
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/network/utils.py
code served (permissive licence) · get_code("ceca25f872bfae7f")
How it ran

no invocation recorded.

deeplabv3_mobilenet Not yet run
unverified (harvested, no recorded run)
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/network/modeling.py
code served (permissive licence) · get_code("395489c4f58f7d7b")
How it ran

no invocation recorded.

deeplabv3_resnet101 Not yet run
unverified (harvested, no recorded run)
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/network/modeling.py
code served (permissive licence) · get_code("ced2abecfa48dbf8")
How it ran

no invocation recorded.

deeplabv3_resnet50 Not yet run
unverified (harvested, no recorded run)
Jun-CEN/Open-World-Semantic-Segmentation/DeepLabV3Plus-Pytorch/network/modeling.py
code served (permissive licence) · get_code("4de0af0762139e5b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 5 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
stable_cumsum 29 other papers
4 dated earlier, 25 later · 1 only as an assembly brick
1911.11132 (2019-11)
Scaling Out-of-Distribution Detection for Real-World Settings
2003.08440 (2020-03)
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
2104.08812 (2021-04)
Contrastive Out-of-Distribution Detection for Pretrained Transformers
and 26 more not named here
convert_to_separable_conv 10 other papers
4 dated earlier, 1 the same month, 4 later, 1 same year, order not determinable
1706.05587 (2017-06)
Rethinking Atrous Convolution for Semantic Image Segmentation
1905.03561 (2019-05)
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
2007.07984 (2020-07)
Leveraging Category Information for Single-Frame Visual Sound Source Separation
and 7 more not named here
fpr_and_fdr_at_recall 8 other papers
2 dated earlier, 6 later
1911.11132 (2019-11)
Scaling Out-of-Distribution Detection for Real-World Settings
2003.08440 (2020-03)
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
aaai_20752 (2022 (year only))
Provable Guarantees for Understanding Out-of-Distribution Detection
and 5 more not named here
get_measures 8 other papers
2 dated earlier, 6 later
1911.11132 (2019-11)
Scaling Out-of-Distribution Detection for Real-World Settings
2003.08440 (2020-03)
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
aaai_20752 (2022 (year only))
Provable Guarantees for Understanding Out-of-Distribution Detection
and 5 more not named here
deeplabv3_resnet50 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
1706.05587 (2017-06)
Rethinking Atrous Convolution for Semantic Image Segmentation
2106.04463 (2021-06)
A multi-centre polyp detection and segmentation dataset for generalisability assessment
and 1 more not named here
deeplabv3_mobilenet 2 other papers
1 dated earlier, 1 same year, order not determinable
Jain_Scaling_Semantic_Segmentation_Beyond_1K_Classes_on_a_Single_GPU_ICCV_2021_paper (2021 (year only))
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
2106.04463 (2021-06)
A multi-centre polyp detection and segmentation dataset for generalisability assessment
deeplabv3_resnet101 2 other papers
1 dated earlier, 1 same year, order not determinable
Jain_Scaling_Semantic_Segmentation_Beyond_1K_Classes_on_a_Single_GPU_ICCV_2021_paper (2021 (year only))
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
2106.04463 (2021-06)
A multi-centre polyp detection and segmentation dataset for generalisability assessment

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

Classical close-set semantic segmentation networks have limited ability to detect out-of-distribution (OOD) objects, which is important for safety-critical applications such as autonomous driving. Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models. In this paper, we propose an open world semantic segmentation system that includes two modules: ( 1) an open-set semantic segmentation module to detect both in-distribution and OOD objects. (2) an incremental few-shot learning module to gradually incorporate those OOD objects into its existing knowledge base. This open world semantic segmentation system behaves like a human being, which is able to identify OOD objects and gradually learn them with corresponding supervision. We adopt the Deep Metric Learning Network (DMLNet) with contrastive clustering to implement open-set semantic segmentation. Compared to other open-set semantic segmentation methods, our DMLNet achieves state-of-the-art performance on three challenging open-set semantic segmentation datasets without using additional data or generative models. On this basis, two incremental few-shot learning methods are further proposed to progressively improve the DMLNet with the annotations of OOD objects.

For agents

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

get_harvested_code_for_paper("2108.04562")
get_code_for_paper("2108.04562")
have("2108.04562")

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

curl https://syntology.ai/api/ran/2108.04562.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.04562.svg)](https://syntology.ai/paper/2108.04562)

Connect an agent — have() is free.