SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.14119 · 2020

Asymmetric Loss For Multi-Label Classification

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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 6 have no contract verdict; 4 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/2009.14119.json · badge: /api/ran/2009.14119.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
mrT23/TResNet canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
SlongLiu/ASL_reproduce community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
average_precision Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SlongLiu/ASL_reproduce/src/helper_functions/helper_functions.py
pointer only (licence: MIT); the stored copy get_code serves, from kjmillerCURIS/SPARC, is pointer only (licence: NONE) · get_code("f52b226226096fdd")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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.

conv2d Ran
ran; our contract draft was wrong, not the code
SlongLiu/ASL_reproduce/src/models/tresnet/tresnet.py
pointer only (licence: MIT) · get_code("ad1cabd96edaffc7")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
mrT23/TResNet/src/models/tresnet_v2/tresnet_v2.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from amerch/CIFAR100-Training, is pointer only (licence: NONE) · get_code("583f9780bdd00a45")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from amerch/CIFAR100-Training, 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.

conv3x3_depth Ran
ran on a synthesized input
mrT23/TResNet/src/models/tresnet_v2/tresnet_v2.py
code served (permissive licence) · get_code("92502509d71ac473")
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 Conv2d. 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 = {
    "planes": 64,
    "stride": 1
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
create_dataloader Ran
ran on a synthesized input
mrT23/TResNet/src/helper_functions/helper_functions.py
code served (permissive licence) · get_code("df7d18ef933d037a")
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 DataLoader. 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
from torchvision import transforms
from torchvision.datasets import ImageFolder
import tempfile
import os
from PIL import Image

torch.manual_seed(0)

# Create a temporary directory with minimal image data for ImageFolder
temp_dir = tempfile.mkdtemp()
val_dir = os.path.join(temp_dir, 'val')
os.makedirs(val_dir, exist_ok=True)

# Create a minimal class subdirectory with a dummy image
class_dir = os.path.join(val_dir, 'class0')
os.makedirs(class_dir, exist_ok=True)

# Create a small dummy image file
dummy_img = Image.new('RGB', (64, 64), color='red')
dummy_img.save(os.path.join(class_dir, 'dummy.jpg'))

# Define arguments class
class Args:
    def __init__(self):
        self.batch_size = 2
        self.input_size = 224
        self.val_zoom_factor = 1.25
        self.val_dir = val_dir
        self.num_workers = 0

ARGS = {
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
mAP Ran
ran on a synthesized input
SlongLiu/ASL_reproduce/src/helper_functions/helper_functions.py
pointer only (licence: MIT) · get_code("0759c5625039d127")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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.

parse_args Ran
ran; our contract draft was wrong, not the code
SlongLiu/ASL_reproduce/src/helper_functions/helper_functions.py
pointer only (licence: MIT); the stored copy get_code serves, from xiemk/mlc-pat, is pointer only (licence: NONE) · get_code("044fe3f67aac5e39")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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.

setup_logger Ran
ran on a synthesized input
SlongLiu/ASL_reproduce/src/helper_functions/logger.py
pointer only (licence: MIT) · get_code("55faa58ee2b0d1b7")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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.

str_to_list Ran
ran on a synthesized input
SlongLiu/ASL_reproduce/src/helper_functions/nuswide_asl.py
pointer only (licence: MIT) · get_code("50a335a67cb29af0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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.

validate Ran
ran on a synthesized input
mrT23/TResNet/src/helper_functions/helper_functions.py
code served (permissive licence) · get_code("db31998e52bea4c8")
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 AverageMeter. 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 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 a minimal model that takes input and produces output
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, num_classes=5):
        super().__init__()
        self.fc = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.fc(x)

# Create the model
model = SimpleModel(input_dim=4, num_classes=5)

# Create a minimal data loader (list of batches with input and target tensors)
val_loader = [
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
]

ARGS = {
    'model': model,
    'val_loader': val_loader,
}
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 AverageMeter — a AverageMeter output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AverageMeter 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
accuracy Not yet run
unverified (harvested, no recorded run)
mrT23/TResNet/src/helper_functions/helper_functions.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kkonstantinidis/ByzShield, is pointer only (licence: NONE) · get_code("4d3faaaa1c706b0b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kkonstantinidis/ByzShield, 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. No invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
SlongLiu/ASL_reproduce/src/models/utils/factory.py
pointer only (licence: MIT) · get_code("f046cb82f2f2f60a")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, SlongLiu/ASL_reproduce, 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 6 later) and 6 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
conv3x3 686 other papers
257 dated earlier, 3 the same month, 425 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
accuracy 23 other papers
14 dated earlier, 9 later
1603.07285 (2016-03)
A guide to convolution arithmetic for deep learning
1608.07017 (2016-08)
Ambient Sound Provides Supervision for Visual Learning
1608.08710 (2016-08)
Pruning Filters for Efficient ConvNets
and 20 more not named here
average_precision 7 other papers
7 later
2111.12933 (2021-11)
ML-Decoder: Scalable and Versatile Classification Head
2112.07368 (2021-12)
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
and 4 more not named here
conv2d 3 other papers
3 later
2111.12933 (2021-11)
ML-Decoder: Scalable and Versatile Classification Head
2403.07603 (2024-03)
ProPML: Probability Partial Multi-label Learning
2403.12559 (2024-03)
Confidence Self-Calibration for Multi-Label Class-Incremental Learning
mAP 3 other papers
3 later
2111.12933 (2021-11)
ML-Decoder: Scalable and Versatile Classification Head
2112.07368 (2021-12)
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
parse_args 2 other papers
2 later
2112.07368 (2021-12)
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
2404.06287 (2024-04)
Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training

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

In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive labels during training, resulting in poor accuracy. In this paper, we introduce a novel asymmetric loss ("ASL"), which operates differently on positive and negative samples. The loss enables to dynamically down-weights and hard-thresholds easy negative samples, while also discarding possibly mislabeled samples. We demonstrate how ASL can balance the probabilities of different samples, and how this balancing is translated to better mAP scores. With ASL, we reach state-of-the-art results on multiple popular multi-label datasets: MS-COCO, Pascal-VOC, NUS-WIDE and Open Images. We also demonstrate ASL applicability for other tasks, such as single-label classification and object detection. ASL is effective, easy to implement, and does not increase the training time or complexity. Implementation is available at: https://github.com/Alibaba-MIIL/ASL.

For agents

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

get_harvested_code_for_paper("2009.14119")
get_code_for_paper("2009.14119")
have("2009.14119")

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

curl https://syntology.ai/api/ran/2009.14119.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.14119.svg)](https://syntology.ai/paper/2009.14119)

Connect an agent — have() is free.