SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.16047 · CVPR · 2021

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

Lizhen Cui, Chang Liu, Han Yu, Boyang Li, Xuansong Xie, Zhiqi Shen, Chunyan Miao, Peiran Ren, Zhanning Gao

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 1 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/2103.16047.json · badge: /api/ran/2103.16047.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
alibaba-edu/Ranking-based-Instance-Selection marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
Registry Ran
ran on a synthesized input · constructed an object; no result was computed
alibaba-edu/Ranking-based-Instance-Selection/ret_benchmark/losses/PRISM.py
code served (permissive licence) · get_code("d5ea45050aa7cd97")
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 an instance of its own class, Registry: the run constructed the object and did not call it, so no result was computed. 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)

# The Registry class is a dict subclass, so we need to construct valid arguments
# for the dict.__init__ method that Registry inherits from.
# Looking at the docstring, Registry can be initialized with an optional dictionary
# of initial modules (e.g., {"default": default_module})

# Create some simple callable modules to register
def default_module():
    """A simple default module function"""
    return "default"

def foo_module():
    """A simple foo module function"""
    return "foo"

class SimpleModule(nn.Module):
    """A minimal nn.Module"""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create initial registry dict with some default entries
initial_registry = {
    "default": default_module,
    "simple": SimpleModule()
}

# The Registry.__init__ accepts *args and **kwargs that are passed to dict.__init__
# We can pass the initial dictionary as a positional argument or as keyword arguments
ARGS = {
    "args": (initial_registry,),
    "kwargs": {}
}
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 Registry — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Registry 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
PRISM Not yet run
unverified (harvested, no recorded run)
alibaba-edu/Ranking-based-Instance-Selection/ret_benchmark/losses/PRISM.py
code served (permissive licence) · get_code("daa1d034e7b8f4ff")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
Registry
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2107.03377 (2021-07)
Long Short-Term Transformer for Online Action Detection
2308.07893 (2023-08)
Memory-and-Anticipation Transformer for Online Action Understanding

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

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) . PRISM identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network. These features are stored in and retrieved from a memory bank. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers. In extensive comparisons with 12 existing approaches under both synthetic and real-world label noise, PRISM demonstrates superior performance of up to 6.06% in Precision@1.

For agents

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

get_harvested_code_for_paper("2103.16047")
get_code_for_paper("2103.16047")
have("2103.16047")

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

curl https://syntology.ai/api/ran/2103.16047.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.16047.svg)](https://syntology.ai/paper/2103.16047)

Connect an agent — have() is free.