SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.09249 · NeurIPS · 2022

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

Jiashi Feng, Yifan Zhang, Bryan Hooi, Lanqing Hong

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 1 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/2107.09249.json · badge: /api/ran/2107.09249.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
Vanint/TADE-AgnosticLT canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
Vanint/TADE-AgnosticLT/model/metric.py
pointer only (licence: MIT); the stored copy get_code serves, from fistyee/mdcs, is pointer only (licence: NONE) · get_code("1c1fdcd838303a0d")
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 fistyee/mdcs, 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.

focal_loss Ran
ran; our contract draft was wrong, not the code
Vanint/TADE-AgnosticLT/model/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from tmlr-group/atol, is pointer only (licence: NONE) · get_code("4dcf06ba28983266")
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 tmlr-group/atol, 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.

learing_rate_scheduler Ran
ran; our contract draft was wrong, not the code
Vanint/TADE-AgnosticLT/train_places.py
pointer only (licence: MIT); the stored copy get_code serves, from fistyee/mdcs, is pointer only (licence: NONE) · get_code("23198d10b9f73030")
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 fistyee/mdcs, 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.

top_k_acc Ran
ran; our contract draft was wrong, not the code
Vanint/TADE-AgnosticLT/model/metric.py
pointer only (licence: MIT); the stored copy get_code serves, from fistyee/LTRL, is pointer only (licence: NONE) · get_code("c642158604bebe8a")
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 fistyee/LTRL, 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.

transform_convert Ran
ran on a synthesized input
Vanint/TADE-AgnosticLT/selection_from_cifar_pool_balance.py
code served (permissive licence) · get_code("bf3d5219dca41ccd")
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 Image. 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
import torchvision.transforms as transforms
import numpy as np
import PIL

torch.manual_seed(0)

# Create a normalized transform pipeline
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# Create a tensor with shape (C, H, W) = (3, 4, 5) representing a normalized image
# The function expects normalized values (after ToTensor and Normalize)
img_tensor = torch.randn(3, 4, 5, dtype=torch.float32)

ARGS = {
    'img_tensor': img_tensor,
    'transform': transform
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
init_weights Not yet run
unverified (harvested, no recorded run)
Vanint/TADE-AgnosticLT/model/model.py
pointer only (licence: MIT); the stored copy get_code serves, from fistyee/LTRL, is pointer only (licence: NONE) · get_code("0933d643f92c12aa")
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 fistyee/LTRL, 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.

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, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
focal_loss 14 other papers
1 dated earlier, 13 later
1906.07413 (2019-06)
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
2304.09426 (2023-04)
Decoupled Training for Long-Tailed Classification With Stochastic Representations
and 11 more not named here
init_weights 4 other papers
4 later
Aimar_Balanced_Product_of_Calibrated_Experts_for_Long-Tailed_Recognition_CVPR_2023_paper (2023 (year only))
Balanced Product of Calibrated Experts for Long-Tailed Recognition
2306.04621 (2023-06)
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
2308.09922 (2023-08)
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
and 1 more not named here
top_k_acc 4 other papers
4 later
Aimar_Balanced_Product_of_Calibrated_Experts_for_Long-Tailed_Recognition_CVPR_2023_paper (2023 (year only))
Balanced Product of Calibrated Experts for Long-Tailed Recognition
2306.04621 (2023-06)
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
2308.09922 (2023-08)
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
and 1 more not named here
accuracy 3 other papers
3 later
Aimar_Balanced_Product_of_Calibrated_Experts_for_Long-Tailed_Recognition_CVPR_2023_paper (2023 (year only))
Balanced Product of Calibrated Experts for Long-Tailed Recognition
2306.04621 (2023-06)
Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration
2308.09922 (2023-08)
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
learing_rate_scheduler 1 other paper
1 later
2308.09922 (2023-08)
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition

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

Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class distributions often violate this assumption (e.g., being either long-tailed or even inversely long-tailed), which may lead existing methods to fail in real applications. In this paper, we study a more practical yet challenging task, called test-agnostic long-tailed recognition, where the training class distribution is long-tailed while the test class distribution is agnostic and not necessarily uniform. In addition to the issue of class imbalance, this task poses another challenge: the class distribution shift between the training and test data is unknown. To tackle this task, we propose a novel approach, called Self-supervised Aggregation of Diverse Experts, which consists of two strategies: (i) a new skill-diverse expert learning strategy that trains multiple experts from a single and stationary long-tailed dataset to separately handle different class distributions; (ii) a novel test-time expert aggregation strategy that leverages self-supervision to aggregate the learned multiple experts for handling unknown test class distributions. We theoretically show that our self-supervised strategy has a provable ability to simulate test-agnostic class distributions. Promising empirical results demonstrate the effectiveness of our method on both vanilla and test-agnostic long-tailed recognition. Code is available at https://github. com/Vanint/SADE-AgnosticLT.

For agents

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

get_harvested_code_for_paper("2107.09249")
get_code_for_paper("2107.09249")
have("2107.09249")

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

curl https://syntology.ai/api/ran/2107.09249.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.09249.svg)](https://syntology.ai/paper/2107.09249)

Connect an agent — have() is free.