phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | convolutional network depth in large-scale image recognition— “In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.” | |
| claim-type | method— “Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3 × 3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16–19 weight layers.” | |
| method — evidence | — “Our implementation is derived from the publicly available C++ Caffe toolbox (Jia, 2013) (branched out in December 2013), but contains a number of significant modifications, allowing us to perform training and evaluation on multiple GPUs installed in a single system, as well as train and evaluate on full-size (uncropped) images at multiple… | |
| mechanism | 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— “a thorough evaluation of networks of increasing depth using an architecture with very small” | mechanisms[0] |
| extends | prior convolutional network configurations— “a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16–19 weight layers” | claim_relations[0] |
| builds-on | Krizhevsky et al. (2012) ConvNet training procedure— “The ConvNet training procedure generally follows Krizhevsky et al. (2012) (except for sampling the input crops from multi-scale training images, as explained later).” | claim_relations[1] |
| extends | the classical ConvNet architecture of LeCun et al. (1989)— “Notably, we did not depart from the classical ConvNet architecture of LeCun et al. (1989), but improved it by substantially increasing the depth.” | claim_relations[2] |
| extends | Ciresan et al. (2011) small-filter networks— “Small-size convolution filters have been previously used by Ciresan et al. (2011), but their nets are significantly less deep than ours, and they did not evaluate on the large-scale ILSVRC dataset.” | claim_relations[3] |
| sense | 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— “and differ only in the depth: from 11 weight layers in the network A (8 conv. and 3 FC layers) to 19 weight layers in the network E (16 conv. and 3 FC layers)” | senses[0] |
| sense | 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— “In this paper, we address another important aspect of ConvNet architecture design” | senses[1] |
| sense | 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'— “It was demonstrated that the representation depth is beneficial for the classification accuracy, and that state-of-the-art performance on the ImageNet challenge dataset can be achieved using a conventional ConvNet architecture (LeCun et al., 1989; Krizhevsky et al., 2012) with substantially increased depth” | senses[2] |
| control | multi-crop and dense evaluation run against each other, and in combination — held — rules out an accuracy figure that belongs to one evaluation protocol - running both shows what the protocol contributes and what the network does— “As can be seen, using multiple crops performs slightly better than dense evaluation, and the two approaches are indeed complementary, as their combination outperforms each of them.” | controls[0] |
| edge | depth —operationalised-as→ weight layers— “and differ only in the depth: from 11 weight layers in the network A (8 conv. and 3 FC layers) to 19 weight layers in the network E (16 conv. and 3 FC layers)” | concept_edges[0] |
| audit | depth —causes→ implicit regularisation — 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.— “We conjecture that in spite of the larger number of parameters and the greater depth of our nets compared to (Krizhevsky et al., 2012), the nets required less epochs to converge due to (a) implicit regularisation imposed by greater depth” | concept_edges[1] |
| weight | depth —causes→ implicit regularisation — 0.6— “We conjecture that in spite of the larger number of parameters and the greater depth of our nets compared to (Krizhevsky et al., 2012), the nets required less epochs to converge due to (a) implicit regularisation imposed by greater depth” | concept_edges[1] |
| outcome (stated by the tagger, no quotation) | control — held | controls[0] |
| for which use | limitation — 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] |
| for which use | limitation — 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] |
| for which use | limitation — 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 Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[2] |
| for which use | limitation — a comparison between these networks and others: all the configurations compared here were designed using the same principles in order to isolate depth Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[3] |
| for which use | limitation — 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 Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
| replication | untested | |
| limitation | Accuracy stops improving once depth reaches 19 layers on this dataset, so the depth benefit is shown to saturate. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[0] |
| limitation | The approach is computationally expensive: a single network takes weeks to train even on four high-end GPUs. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[1] |
| limitation | The depth result is licensed by a control: every other parameter was deliberately held fixed. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[2] |
| limitation | The configurations being compared were built to one recipe, which is what makes the comparison fair and also what bounds it. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[3] |
| limitation | The explanation offered for faster convergence is labelled a conjecture by the authors. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | 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 paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[0] |
| evidence status note | finding — 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] |
| finding | The learned deep representations generalise well, achieving state-of-the-art results on other image datasets. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[1] |
| quantity | 3 × 3 — very small convolution filter (receptive field) used throughout the network Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[0] |
| quantity | 16–19 weight layers — network depth that yields the improvement Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[1] |
| quantity | 1000 classes — ILSVRC classification output dimension Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[2] |
| evidence status note | quantity — 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] |
| variable | convolutional network depth (independent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[0] |
| definition | top-5 error Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[0] |
| definition | receptive field Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[1] |
| key-terms | convolutional, depth, filters, layers, ImageNet, classification, network, recognition, localisation |
| concept | ConvNet Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[4] |
| concept | weight layers Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[5] |
| concept | receptive field Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[6] |
| concept | implicit regularisation Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[7] |
| concept | depth Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[8] |
| regression β | as written: logistic regression Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[1] |
| evidence status note | regression — 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.statistics[1] |
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.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824