SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1311.2901 · ECCV · 2013

Visualizing and Understanding Convolutional Networks

Rob Fergus, Matthew Zeiler

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 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/1311.2901.json · badge: /api/ran/1311.2901.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
NetraInamdar/Deep_Learning_Project community
Papers with Code archive
1 ran · 2 no recorded run
TooTouch/WhiteBox-Part1 community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
DeconvNet Ran
ran on a synthesized input · constructed an object; no result was computed
TooTouch/WhiteBox-Part1/code/saliency/attribution_methods.py
code served (permissive licence) · get_code("faf7178ea79d4f48")
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, DeconvNet: 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)

# Build a minimal model that satisfies DeconvNet's usage
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 8, kernel_size=3, padding=1),
            nn.MaxPool2d(kernel_size=2, stride=2, return_indices=True),
            nn.Conv2d(8, 16, kernel_size=3, padding=1),
        )
        self.classifier = nn.Linear(16 * 2 * 2, 10)
        self.feature_maps = {}
        self.pool_locs = {}
    
    def forward(self, x):
        # Process through features
        for layer in self.features:
            if isinstance(layer, nn.MaxPool2d):
                x, indices = layer(x)
            else:
                x = layer(x)
        # Flatten and classify
        x = x.view(x.size(0), -1)
        x = self.classifier(x)
        return x

class MinimalDeconvModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.deconv_layer = nn.ConvTranspose2d(8, 3, kernel_size=3, padding=1)
    
    def forward(self, feature_maps, layer, pool_locs):
        # Minimal deconvolution operation
        output = self.deconv_layer(feature_maps)
        return output

# Create model instances
model = MinimalModel()
deconv_model = MinimalDeconvModel()

ARGS = {
    'model': model,
    'deconv_model': deconv_model,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DeconvNet — 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 DeconvNet 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
generate_input_bias_values Ran
ran, honoured the contract we drafted
NetraInamdar/Deep_Learning_Project/training.py
pointer only (licence: NONE) · get_code("c4f57d2d76e2e53e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NetraInamdar/Deep_Learning_Project 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.

convolution_layer_implementation Not yet run
unverified (harvested, no recorded run)
NetraInamdar/Deep_Learning_Project/training.py
pointer only (licence: NONE) · get_code("6dd512ac4f5eccbd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NetraInamdar/Deep_Learning_Project 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.

generate_weighted_vectors Not yet run
unverified (harvested, no recorded run)
NetraInamdar/Deep_Learning_Project/training.py
pointer only (licence: NONE) · get_code("812ee6e5ebdabef1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, NetraInamdar/Deep_Learning_Project 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark (Krizhevsky et al., 2012). However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. Used in a diagnostic role, these visualizations allow us to find model architectures that outperform Krizhevsky et al. on the ImageNet classification benchmark. We also perform an ablation study to discover the performance contribution from different model layers. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets.

For agents

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

get_harvested_code_for_paper("1311.2901")
get_code_for_paper("1311.2901")
have("1311.2901")

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

curl https://syntology.ai/api/ran/1311.2901.json

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

[![Syntology run record](https://syntology.ai/api/ran/1311.2901.svg)](https://syntology.ai/paper/1311.2901)

Connect an agent — have() is free.