SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.02721 · ICCV · 2021

Instance Similarity Learning for Unsupervised Feature Representation

Jiwen Lu, Jie Zhou, Ziyi Wu, Ziwei Wang, Yunsong Wang

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 (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; 0 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/2108.02721.json · badge: /api/ran/2108.02721.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
ZiweiWangTHU/ISL community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
LinearCriterion Ran
ran on a synthesized input · constructed an object; no result was computed
ZiweiWangTHU/ISL/lib/LinearAverage.py
code served (permissive licence) · get_code("0d0345432cf88f8c")
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, LinearCriterion: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn
import numpy as np

torch.manual_seed(0)

# Create a simple LinearCriterion instance for testing
# We need to construct: logits, index, aff_mat, memory

batch_size = 2
num_data = 5
emb_size = 4

# logits: [batch, num_data] - raw scores before softmax
logits = torch.randn(batch_size, num_data)

# index: [batch] - indices of image data (values should be in range [0, num_data))
index = torch.tensor([1, 3])

# aff_mat: list of sets storing neighbour relationships for each data
# len(aff_mat) == num_data
# Each element is a set of indices (including itself potentially)
aff_mat = [
    {0},           # data 0 has no neighbors (only itself)
    {1, 2, 3},     # data 1 has neighbors 2, 3
    {2},           # data 2 has no neighbors
    {3, 4},        # data 3 has neighbor 4
    {4}            # data 4 has no neighbors
]

# memory: [num_data, emb_size] - embeddings for all data points
# This is only used when hp_loss_weight > 0 and memory is not None
memory = torch.randn(num_data, emb_size)

ARGS = {
    'hp_loss_weight': 0.0,
    'T': None
}

# Arguments for forward call:
forward_args = {
    'logits': logits,
    'index': index,
    'aff_mat': aff_mat,
    'memory': memory
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LinearCriterion — 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 LinearCriterion 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

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

In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature space with high similarity, which usually leads to wrong pairwise relationship for large neighborhoods because the Euclidean distance fails to depict the true semantic similarity on the feature manifold. On the contrary, our method mines the feature manifold in an unsupervised manner, through which the semantic similarity among instances is learned in order to obtain discriminative representations. Specifically, we employ the Generative Adversarial Networks (GAN) to mine the underlying feature manifold, where the generated features are applied as the proxies to progressively explore the feature manifold so that the semantic similarity among instances is acquired as reliable pseudo supervision. Extensive experiments on image classification demonstrate the superiority of our method compared with the state-of-the-art methods. The code is available at https://github.com/ZiweiWangTHU/ISL.git.

For agents

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

get_harvested_code_for_paper("2108.02721")
get_code_for_paper("2108.02721")
have("2108.02721")

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

curl https://syntology.ai/api/ran/2108.02721.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.02721.svg)](https://syntology.ai/paper/2108.02721)

Connect an agent — have() is free.