Very Deep Convolutional Networks for Large-Scale Image Recognition

Karen Simonyan, Andrew Zisserman · ICLR / arXiv · 2014 · artificial-intelligence · record simonyan2014-vgg
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. Claim type is contestable: the paper's deliverable is an architecture (method), but its stated result is a causal claim about depth ('It was demonstrated that the representation depth is beneficial for the classification accuracy...'), which would read as mechanism. I chose method because the abstract's 'main contribution' sentence frames the paper as an architecture evaluation and the released models are the artefact. The extracted text stops at the conclusion; Appendices A (localisation) and B (generalisation to other datasets) referenced in the paper are not in the supplied file, so no facet draws on them. The comparison with GoogLeNet (Szegedy et al., 2014) is a performance comparison, not one of the four allowed relation types, so it is omitted. 2026-08-14 and 2026-08-25 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
deep learning 11 fields · logistic regression 3 fields · classification 2 fields · convolutional neural network 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 9 concept tags on this paper, 5 are grounded in a quoted sentence.

convolutional neural network network depth image recognition deep learning ConvNet weight layers receptive field implicit regularisation depth stack many very small (3x3) convolution filters to build very deep networks - depth (16-19 layers), not filter size, drives accuracy, while small filters keep parameters low and grow the effective receptive field convolutional filters layers ImageNet classification network recognition localisation top-5 error convolutional network depth regression logistic regression system-or-tool-building

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://arxiv.org/abs/1409.1556. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 4 · claim_type 1 · concept_edges 2 · concepts 5 · content_tags 9 · controls 1 · limitations 5 · mechanisms 1 · method 1 · phenomenon 1 · senses 3

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 2 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	convolutional network depth in large-scale image recognition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: system-or-tool-building	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: stack many very small (3x3) convolution filters to build very deep networks - depth (16-19 layers), not filter size, drives accuracy, while small filters keep parameters low and grow the effective receptive field	`mechanisms[0]`		the tagger's words
limitations	Accuracy stops improving once depth reaches 19 layers on this dataset, so the depth benefit is shown to saturate. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the depth claim on this dataset: THE ERROR RATE OF OUR ARCHITECTURE SATURATES WHEN THE DEPTH REACHES 19 LAYERS, BUT EVEN DEEPER MODELS MIGHT BE BENEFICIAL FOR LARGER DATASETS	`limitations[0]`		the tagger's words
limitations	The approach is computationally expensive: a single network takes weeks to train even on four high-end GPUs. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: anyone planning to reproduce or extend the training: ON A SYSTEM EQUIPPED WITH FOUR NVIDIA TITAN BLACK GPUs, TRAINING A SINGLE NET TOOK 2-3 WEEKS	`limitations[1]`		the tagger's words
limitations	The depth result is licensed by a control: every other parameter was deliberately held fixed. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the claim that depth improves accuracy: the authors fixed the other architectural parameters and increased depth alone, so the result holds for the family of configurations that control defines	`limitations[2]`	1.0	the tagger's words
limitations	The configurations being compared were built to one recipe, which is what makes the comparison fair and also what bounds it. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: a comparison between these networks and others: all the configurations compared here were designed using the same principles in order to isolate depth	`limitations[3]`	1.0	the tagger's words
limitations	The explanation offered for faster convergence is labelled a conjecture by the authors. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the claim that greater depth speeds convergence: the authors conjecture the nets required fewer epochs owing to implicit regularisation imposed by greater depth and smaller filters	`limitations[4]`	1.0	the tagger's words
controls	multi-crop and dense evaluation run against each other, and in combination Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: an accuracy figure that belongs to one evaluation protocol - running both shows what the protocol contributes and what the network does · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.85	the tagger's words
concepts	ConvNet Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ConvNet	`concepts[4]`		the paper's words
concepts	weight layers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: weight layers	`concepts[5]`		the paper's words
concepts	receptive field Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: receptive field	`concepts[6]`		the paper's words
concepts	implicit regularisation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: implicit regularisation	`concepts[7]`		the paper's words
concepts	depth Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: depth	`concepts[8]`		the paper's words
senses	depth - AS A COUNT OF WEIGHT LAYERS: the configurations differ only in this number, from 11 in network A to 19 in E, so 'depth' here is an integer in a controlled series and not a general property of an architecture Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	ConvNet - THE PAPER'S OWN WORD, AND THE ONLY ONE IT USES: it says ConvNet 44 times and never writes 'convolutional neural network' or 'deep learning', both of which this record is filed under; the expanded name and the field's later label are absent from the paper that made them famous Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	the conclusion - ABOUT REPRESENTATION DEPTH ON A CONVENTIONAL ARCHITECTURE: the paper's own summary is that depth is beneficial and that the state of the art can be reached with a conventional architecture substantially deepened, which is a narrower claim than 'deeper is better' Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
claim_relations	extends → prior convolutional network configurations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	builds-on → Krizhevsky et al. (2012) ConvNet training procedure Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	extends → the classical ConvNet architecture of LeCun et al. (1989) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
claim_relations	extends → Ciresan et al. (2011) small-filter networks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`		the tagger's words
concept_edges	depth —operationalised-as→ weight layers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: depth · weight layers	`concept_edges[0]`		the tagger's words
concept_edges	depth —causes→ implicit regularisation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 0.6 — the record marks this weak Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says 'we conjecture' the faster convergence is due to implicit regularisation; hedged. also in: depth · implicit regularisation	`concept_edges[1]`		the tagger's words
content_tags	3 × 3 — very small convolution filter (receptive field) used throughout the network Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	16–19 — network depth that yields the improvement Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	1000 — ILSVRC classification output dimension Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE RECOVERED FROM THE PAPER'S OWN CHARACTERS. The recorded quote was LETTERS-ONLY IDENTICAL to this stretch of the staged text but not an exact substring of it - spaces, hyphens, ligature glyphs or mathematical operators differed, so it could never anchor. This is the file's own text between the same two letters: not produced by a rule about the damage, copied out of the file. Round-trip checked (the recovered span is letters-only equal to the original) and length-checked. The text as originally recorded is kept in evidence as extracted.	`content_tags.quantities[2]`		the tagger's words
content_tags	Pushing ConvNet depth to 16-19 weight layers was the basis of an ImageNet Challenge 2014 submission that took first place in localisation and second in classification. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted.	`content_tags.findings[0]`		the tagger's words
content_tags	The learned deep representations generalise well, achieving state-of-the-art results on other image datasets. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`		the tagger's words
content_tags	convolutional network depth Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: convolutional network depth	`content_tags.variables[0]`		the tagger's words
content_tags	top-5 error Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: top-5 error	`content_tags.definitions[0]`		the tagger's words
content_tags	receptive field Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: receptive field	`content_tags.definitions[1]`		the tagger's words
content_tags	regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE RECOVERED FROM THE PAPER'S OWN CHARACTERS. The recorded quote was LETTERS-ONLY IDENTICAL to this stretch of the staged text but not an exact substring of it - spaces, hyphens, ligature glyphs or mathematical operators differed, so it could never anchor. This is the file's own text between the same two letters: not produced by a rule about the damage, copied out of the file. Round-trip checked (the recovered span is letters-only equal to the original) and length-checked. The text as originally recorded is kept in evidence as extracted. also in: regression	`content_tags.statistics[1]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.