SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13606 · ICCV · 2023

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

Tinne Tuytelaars, Jean-Philippe Thiran, K Leuven, Tim Lebailly, Behzad Bozorgtabar, Chuv, Thomas Stegmüller

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; 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/2303.13606.json · badge: /api/ran/2303.13606.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
tileb1/AdaSim community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
AdaSimLoss Ran
ran on a synthesized input · constructed an object; no result was computed
tileb1/AdaSim/adasim_utils/loss.py
code served (permissive licence) · get_code("66b37bceaaacfe02")
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, AdaSimLoss: 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
import numpy as np

torch.manual_seed(0)

# Mock distributed environment
class MockDist:
    @staticmethod
    def all_reduce(tensor):
        pass
    
    @staticmethod
    def get_world_size():
        return 1

import torch.distributed as dist
dist.all_reduce = MockDist.all_reduce
dist.get_world_size = MockDist.get_world_size

# Create a minimal args object with required attributes
class Args:
    def __init__(self):
        self.local_crops_number = 2
        self.batch_size_per_gpu = 2

# Define dimensions
out_dim = 4
ncrops = 4
batch_size_per_gpu = 2
num_crops_total = 2 + 2  # 2 global + 2 local

# Create sample outputs
# Student output: (batch_size_per_gpu * num_crops_total, out_dim) + feature tensor
student_output_logits = torch.randn(batch_size_per_gpu * num_crops_total, out_dim)
student_output_feat = torch.randn(batch_size_per_gpu * num_crops_total, out_dim)
student_output = (student_output_logits, student_output_feat)

# Teacher output: (batch_size_per_gpu * 2, out_dim) + feature tensor
teacher_output_logits = torch.randn(batch_size_per_gpu * 2, out_dim)
teacher_output_feat = torch.randn(batch_size_per_gpu * 2, out_dim)
teacher_output = (teacher_output_logits, teacher_output_feat)

args = Args()
epoch = 0

ARGS = {
    'out_dim': out_dim,
    'ncrops': ncrops,
    'warmup_teacher_temp': 0.04,
    'teacher_temp': 0.07,
    'warmup_teacher_temp_epochs': 30,
    'nepochs': 100,
    'student_temp': 0.1,
    'center_momentum': 0.9,
    'args': args,
}
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 AdaSimLoss — 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 AdaSimLoss 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

Most self-supervised methods for representation learning leverage a cross-view consistency objective i.e. they maximize the representation similarity of a given image's augmented views. Recent work NNCLR goes beyond the cross-view paradigm and uses positive pairs from different images obtained via nearest neighbor bootstrapping in a contrastive setting. We empirically show that as opposed to the contrastive learning setting which relies on negative samples, incorporating nearest neighbor bootstrapping in a self-distillation scheme can lead to a performance drop or even collapse. We scrutinize the reason for this unexpected behavior and provide a solution. We propose to adaptively bootstrap neighbors based on the estimated quality of the latent space. We report consistent improvements compared to the naive bootstrapping approach and the original baselines. Our approach leads to performance improvements for various self-distillation method/backbone combinations and standard downstream tasks. Our code is publicly available at https://github.com/tileb1/AdaSim. * denotes equal contribution.

For agents

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

get_harvested_code_for_paper("2303.13606")
get_code_for_paper("2303.13606")
have("2303.13606")

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

curl https://syntology.ai/api/ran/2303.13606.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.13606.svg)](https://syntology.ai/paper/2303.13606)

Connect an agent — have() is free.