SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper · CVPR · 2022

Incremental Learning in Semantic Segmentation from Image Labels

Marco Ciccone, Barbara Caputo, Politecnico Torino, Fabio Cermelli, Dario Fontanel, Antonio Tavera

Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 3 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/Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper.json · badge: /api/ran/Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper.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
fcdl94/WILSON canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
get_loss Ran
ran; our contract draft was wrong, not the code
fcdl94/WILSON/utils/loss.py
code served (permissive licence) · get_code("1d5ab3d2728d692e")
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 FocalLoss. 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)

# Define test arguments for get_loss function
ARGS = {
    'loss_type': 'focal_loss'
}
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 FocalLoss — a FocalLoss output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a FocalLoss 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
modify_command_options Ran
ran on a synthesized input
fcdl94/WILSON/argparser.py
code served (permissive licence) · get_code("9f6571860fc4bba7")
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 Options. 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.

class Options:
    def __init__(self):
        self.dataset = 'voc'
        self.num_classes = None
        self.visualize = True
        self.sample_num = 5
        self.backbone = 'resnet50'
        self.output_stride = 16
        self.crop_size = 512
        self.crop_size_val = 512
        self.new_protocol = False
        self.overlap = True
        self.no_overlap = None
        self.pooling = None
        self.step = 1
        self.lr_head = 0.001

opts = Options()

ARGS = {
    'opts': opts
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 Options — a Options output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Options 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
next_free_port Ran
ran, honoured the contract we drafted
fcdl94/WILSON/get_free_port.py
pointer only (licence: MIT); the stored copy get_code serves, from prinshul/JASCL, is pointer only (licence: NONE) · get_code("5bb42fad3fc38eff")
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 prinshul/JASCL, 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_per_task_classes Not yet run
unverified (harvested, no recorded run)
fcdl94/WILSON/tasks.py
code served (permissive licence) · get_code("e4a90772bfb067a5")
How it ran

no invocation recorded.

get_task_dict Not yet run
unverified (harvested, no recorded run)
fcdl94/WILSON/tasks.py
code served (permissive licence) · get_code("0fa572a5c16f0f84")
How it ran

no invocation recorded.

get_task_labels Not yet run
unverified (harvested, no recorded run)
fcdl94/WILSON/tasks.py
code served (permissive licence) · get_code("0532a0e37b3de595")
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, 1 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
next_free_port 3 other papers
2 later, 1 same year, order not determinable
2210.02326 (2022-10)
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
2407.11499 (2024-07)
Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection
2605.20538 (2026-05)
Continual Segmentation under Joint Nonstationarity
get_loss 2 other papers
1 dated earlier, 1 same year, order not determinable
2002.00718 (2020-02)
Modeling the Background for Incremental Learning in Semantic Segmentation
2210.07207 (2022-10)
Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic 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

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudolabels offline, we use a localizer, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the localizer. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision. 1 * Equal contribution 1 Code can be found at https://github.com/fcdl94/WILSON.

For agents

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

get_harvested_code_for_paper("Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper")
get_code_for_paper("Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper")
have("Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper")

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

curl https://syntology.ai/api/ran/Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper.json

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

[![Syntology run record](https://syntology.ai/api/ran/Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper.svg)](https://syntology.ai/paper/Cermelli_Incremental_Learning_in_Semantic_Segmentation_From_Image_Labels_CVPR_2022_paper)

Connect an agent — have() is free.