SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.05474 · NeurIPS · 2021

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

Liwei Wang, Fangyun Wei, Hanzhe Hu, Qiwei Ye, Jinshi Cui, Ema Update

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 1 has no contract verdict; 0 failures of our instrument; 0 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/2110.05474.json · badge: /api/ran/2110.05474.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
hzhupku/semiseg-ael community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Criterion_cons Ran
ran on a synthesized input
hzhupku/semiseg-ael/semseg/utils/loss_helper.py
code served (permissive licence) · get_code("df89ce7c7fa936b9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn

class Criterion_cons(nn.Module):

    def __init__(self, gamma, sample=False, gamma2=1, ignore_index=255, thresh=0.7, min_kept=100000, use_weight=False):
        super(Criterion_cons, self).__init__()
        self.gamma = gamma
        self.gamma2 = float(gamma2)
        self._ignore_index = ignore_index
        self.sample = sample
        self._criterion = nn.CrossEntropyLoss(ignore_index=ignore_index, reduction='none')

    def forward(self, preds, conf, gt, dcp_criterion=None):
        ce_loss = self._criterion(preds, gt)
        conf = torch.pow(conf, self.gamma)
        if self.sample:
            dcp_criterion = 1 - dcp_criterion
            dcp_criterion = dcp_criterion / (torch.max(dcp_criterion) + 1e-12)
            dcp_criterion = torch.pow(dcp_criterion, self.gamma2)
            pred_map = preds.max(1)[1].float()
            sample_map = torch.zeros_like(pred_map).float()
            h, w = (pred_map.shape[-2], pred_map.shape[-1])
            for idx in range(len(dcp_criterion)):
                prob = 1 - dcp_criterion[idx]
                rand_map = torch.rand(h, w) * (pred_map == idx)
                rand_map = (rand_map > prob) * 1.0
                sample_map += rand_map
            conf = conf * sample_map
        conf = conf / (conf.sum() + 1e-12)
        loss = conf * ce_loss
        return loss.sum()


INIT_ARGS = {
    'gamma': 0.5,
    'sample': False,
    'gamma2': 1.0,
    'ignore_index': 255,
    'thresh': 0.7,
    'min_kept': 100000,
    'use_weight': False,
}

ARGS = {
    'preds': torch.randn(2, 4, 3, 5),
    'conf': torch.rand(2, 3, 5),
    'gt': torch.randint(0, 4, (2, 3, 5)),
    'dcp_criterion': None,
}

if __name__ == '__main__':
    criterion = Criterion_cons(**INIT_ARGS)
    output = criterion(**ARGS)
    print(f"Output: {output}")
    print(f"Output shape: {output.shape if hasattr(output, 'shape') else 'scalar'}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 0, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution. Existing approaches almost all neglect this problem, and treat categories equally. Some popular approaches such as consistency regularization or pseudo-labeling may even harm the learning of under-performing categories, that the predictions or pseudo labels of these categories could be too inaccurate to guide the learning on the unlabeled data. In this paper, we look into this problem, and propose a novel framework for semi-supervised semantic segmentation, named adaptive equalization learning (AEL). AEL adaptively balances the training of well and badly performed categories, with a confidence bank to dynamically track category-wise performance during training. The confidence bank is leveraged as an indicator to tilt training towards under-performing categories, instantiated in three strategies: 1) adaptive Copy-Paste and CutMix data augmentation approaches which give more chance for under-performing categories to be copied or cut; 2) an adaptive data sampling approach to encourage pixels from under-performing category to be sampled; 3) a simple yet effective re-weighting method to alleviate the training noise raised by pseudo-labeling. Experimentally, AEL outperforms the state-of-the-art methods by a large margin on the Cityscapes and Pascal VOC benchmarks under various data partition protocols. Code is available at https://github.com/hzhupku/SemiSeg-AEL.

For agents

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

get_harvested_code_for_paper("2110.05474")
get_code_for_paper("2110.05474")
have("2110.05474")

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

curl https://syntology.ai/api/ran/2110.05474.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.05474.svg)](https://syntology.ai/paper/2110.05474)

Connect an agent — have() is free.