A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS

Juan Terven, Diana‐Margarita Córdova‐Esparza, Julio-Alejandro Romero-González · Machine Learning and Knowledge Extraction · 2023 · artificial-intelligence · 10.3390/make5040083 · record terven2023-a-comprehensive-review-of-yolo-arc
tag layer · index · concepts · authors · עברית

Where this record's text came from. 2026-08-22 and 2026-08-28 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.

This record’s own method is review, and the tags below follow from that. A review’s findings, quantities and statistics are things stated IN this paper, and some of them report results obtained elsewhere. No tag on this page names a different author. Measured across every review in this corpus, 81% of a review’s tags carry no citation at all — most of them are the review speaking. The corpus does not adjudicate the rest: read an unmarked tag as a claim this paper makes, not necessarily one it made first.

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 WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below.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 An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason.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
precision 10 fields · recall 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 16 concept tags on this paper, all 16 are grounded in a quoted sentence. All carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

average precision Intersection over Union precision recall Non-maximum suppression post-processing technique YOLO You Only Look Once single pass two-steps anchor boxes prior boxes Dimension clusters objectness score backbone architecture Darknet-19 confidence threshold review

Method, as described: narrative review of each YOLO release, with a metrics section deriving AP for both the PASCAL VOC and the Microsoft COCO conventions

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
contribution	`contribution`	what the paper claims to add
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
object of study	`object_of_study`	what the paper is about — the thing it investigates
phenomenon	`phenomenon`	the effect or regularity under study
research question	`research_question`	the question the paper sets itself
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
unrecordable relation	`unhoused_relations`	a relation the paper asserts that this vocabulary cannot express, with the reason

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://doi.org/10.3390/make5040083. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 2 · claim_type 1 · concept_edges 3 · concepts 16 · content_tags 13 · contribution 1 · controls 3 · limitations 4 · mechanisms 2 · method 1 · object_of_study 1 · phenomenon 1 · research_question 1 · senses 16 · unhoused_relations 1

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; 3 of 3 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
object_of_study	the YOLO family of real-time object detectors from v1 to v8, and the single number the whole family is ranked by Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`object_of_study`		the paper's words
research_question	what changed architecturally at each YOLO iteration, and on what measure the improvements are quoted Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`research_question`		the paper's words
contribution	a version-by-version account of the architecture changes, prefaced by an explanation of the evaluation metric that shows it is not one metric Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`contribution`		the paper's 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	real-time object detection, whose published progress is stated almost entirely in points of AP 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	review Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: review	`method`		the paper's words
mechanisms	AP is built on the precision-recall curve, and precision and recall trade against each other - detecting more objects raises recall and produces more false positives - so the single number is an area under a curve, not a count Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[0]`	0.95	the tagger's words
mechanisms	what counts as a correct detection at all is set by an IoU threshold, and COCO averages over a RANGE of thresholds from 0.5 to 0.95 - so the definition of `correct` is itself a parameter being averaged over Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[1]`	0.95	the tagger's words
limitations	TWO NAMES FOR ONE THING: `average precision (AP), traditionally called mean average precision (mAP)`, and `The COCO dataset makes no distinction between AP and mAP`. The review has to declare which word it will use before it can use it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[0]`	0.95	the tagger's words
limitations	AND ONE NAME FOR TWO COMPUTATIONS: `The AP is computed differently in the VOC and in the COCO datasets` - 11-point interpolation over 20 categories at one IoU threshold, against 101-point interpolation over 80 categories averaged over ten IoU thresholds Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[1]`	0.95	the tagger's words
limitations	THE CONSEQUENCE IS STATED PLAINLY AND IT IS ABOUT COMPARABILITY: `The differences in AP calculation make it hard to directly compare the performance of object detection models across the two datasets` Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[2]`	0.95	the tagger's words
limitations	the improvements the field reports are quoted in that same word - 2.3 points from simOTA, 2.4 from stronger augmentation - so the increments inherit whatever the number means on the day Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[3]`	0.95	the tagger's words
controls	the review derives AP separately for each dataset convention before reporting any model's score, rather than treating the metric as given Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a reader lining up a YOLOv2 number against a YOLOv5 number - the first is VOC AP and the second is COCO AP, and they are different quantities · outcome: held	`controls[0]`	0.95	the tagger's words
controls	the naming collision is settled explicitly - 'in the rest of this paper, we will refer to this metric as AP' - instead of the two words being used interchangeably Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a review whose own text is ambiguous about which of two names it means, in a document whose whole purpose is to compare numbers · outcome: held	`controls[1]`	0.95	the tagger's words
controls	whether the reported per-version gains are comparable to one another Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: nothing - the gains are quoted in AP points and the review has just shown AP is two computations, so a 2.3-point gain and a 2.4-point gain are only comparable if both were measured under the same convention, which the review does not state per gain · outcome: absent-not-in-staged-text	`controls[2]`	0.85	the tagger's words
concepts	average precision Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: average precision	`concepts[0]`	0.95	the paper's words
concepts	Intersection over Union Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Intersection over Union	`concepts[1]`	0.95	the paper's words
concepts	precision Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: precision	`concepts[2]`	0.95	the paper's words
concepts	recall Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: recall	`concepts[3]`	0.95	the paper's words
concepts	Non-maximum suppression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Non-maximum suppression	`concepts[4]`	0.95	the paper's words
concepts	post-processing technique Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: post-processing technique	`concepts[5]`	0.95	the paper's words
concepts	YOLO Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: YOLO	`concepts[6]`	0.95	the paper's words
concepts	You Only Look Once Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: You Only Look Once	`concepts[7]`	0.95	the paper's words
concepts	single pass Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: single pass	`concepts[8]`	0.95	the paper's words
concepts	two-steps Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: two-steps	`concepts[9]`	0.95	the paper's words
concepts	anchor boxes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: anchor boxes	`concepts[10]`	0.95	the paper's words
concepts	prior boxes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: prior boxes	`concepts[11]`	0.95	the paper's words
concepts	Dimension clusters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Dimension clusters	`concepts[12]`	0.95	the paper's words
concepts	objectness score Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: objectness score	`concepts[13]`	0.95	the paper's words
concepts	backbone architecture Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: backbone architecture	`concepts[14]`	0.95	the paper's words
concepts	Darknet-19 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Darknet-19	`concepts[15]`	0.95	the paper's words
unhoused_relations	YOLO → You Only Look Once Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. YOLO is the acronym that stands for You Only Look Once. Abbreviation expansion is not is-a, part-of, same-as, distinct-from, contrasted-with, operationalised-as, causes, or renamed-across-fields.	`unhoused_relations[0]`	0.95	the tagger's words
senses	AP / mAP - THE SAME QUANTITY UNDER TWO NAMES, and the review says so in its own first metrics sentence. `Traditionally called mean average precision`; COCO makes no distinction; the paper picks `AP` by fiat. A FIELD'S CENTRAL METRIC WITH AN UNSETTLED NAME Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	0.95	the tagger's words
senses	AP, VOC SENSE - 11-point interpolation of the precision-recall curve, averaged over 20 categories, at a single IoU threshold Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	0.95	the tagger's words
senses	AP, COCO SENSE - 101-point interpolation, 80 categories, averaged over IoU thresholds from 0.5 to 0.95 in steps of 0.05. THE SAME SYMBOL AS THE VOC SENSE AND A DIFFERENT QUANTITY, which is why numbers from the two eras of YOLO cannot be lined up Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	0.95	the tagger's words
senses	AP50 - the one COCO figure that is a single-threshold measurement, named separately BECAUSE it is the exception. The existence of a special name for the simple case is the clearest sign that the unqualified word is not simple Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[3]`	0.95	the tagger's words
senses	Non-maximum suppression - post-processes multiple overlapping predictions by retaining the most accurate bounding boxes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[4]`	0.95	the tagger's words
senses	Post-processing technique - NMS is explicitly placed in this method class Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[5]`	0.95	the tagger's words
senses	YOLO - completes object detection through a single network pass rather than proposal generation followed by classification Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[6]`	0.95	the tagger's words
senses	You Only Look Once - the full phrase encoded by the YOLO acronym Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[7]`	0.95	the tagger's words
senses	Single pass - the design choice named by YOLO and contrasted with proposal/classifier pipelines Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[8]`	0.95	the tagger's words
senses	Two-steps - first detect candidate object regions, then classify the region proposals Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[9]`	0.95	the tagger's words
senses	Anchor boxes - predefined shapes that match prototypical object shapes and receive coordinate/class predictions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[10]`	0.95	the tagger's words
senses	Prior boxes - the review's co-occurring name for anchor boxes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[11]`	0.95	the tagger's words
senses	Dimension clusters - k-means-derived box priors balancing recall against model complexity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[12]`	0.95	the tagger's words
senses	Objectness score - YOLOv3 logistic score set to one for the anchor with highest ground-truth overlap Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[13]`	0.95	the tagger's words
senses	Backbone architecture - YOLOv2's feature extractor, called Darknet-19 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[14]`	0.95	the tagger's words
senses	Darknet-19 - a backbone with nineteen convolutional and five max-pooling layers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[15]`	0.95	the tagger's words
claim_relations	critiques → cross-dataset comparison of object detection performance, since AP means a different computation on VOC and on COCO Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`	0.95	the tagger's words
claim_relations	supports → the COCO AP as the current standard, on the ground that it evaluates localisation at a range of IoU thresholds rather than one Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`	0.95	the tagger's words
concept_edges	Non-maximum suppression —is-a→ post-processing technique Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The definition explicitly states that NMS is a post-processing technique. also in: Non-maximum suppression · post-processing technique	`concept_edges[0]`	0.95	the tagger's words
concept_edges	single pass —contrasted-with→ two-steps Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The review contrasts the single network pass with earlier two-step proposal/classifier methods using 'as opposed to'. also in: single pass · two-steps	`concept_edges[1]`	0.95	the tagger's words
concept_edges	backbone architecture —same-as→ Darknet-19 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The review says the YOLOv2 backbone architecture is called Darknet-19. also in: backbone architecture · Darknet-19	`concept_edges[2]`	0.95	the tagger's words
content_tags	TWO NAMES FOR ONE THING: AP is `traditionally called mean average precision (mAP)`, and the COCO dataset makes no distinction between them - so the review declares which word it will use before using it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`	0.95	the tagger's words
content_tags	AND ONE NAME FOR TWO COMPUTATIONS: THE AP IS COMPUTED DIFFERENTLY IN THE VOC AND IN THE COCO DATASETS Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`	0.95	the tagger's words
content_tags	COCO has 80 categories and uses 101-point interpolation, averaging AP over multiple IoU values rather than one, except AP50 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`	0.95	the tagger's words
content_tags	differences in AP calculation make direct comparison of object detection models across the two datasets hard Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[3]`	0.95	the tagger's words
content_tags	simOTA, the simplified version proposed by YOLOX, increased AP by 2.3 points Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[4]`	0.95	the tagger's words
content_tags	the commonly used metric for evaluating object detection, measuring average precision across all categories - traditionally called mean average precision, and COCO makes no distinction between the two Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: average precision	`content_tags.definitions[0]`	0.95	the tagger's words
content_tags	the overlap between the ground truth and predicted bounding boxes, thresholded to decide whether a prediction is a true positive Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Intersection over Union	`content_tags.definitions[1]`	0.95	the tagger's words
content_tags	recall thresholds in the COCO interpolation, against 11 in VOC - and 80 categories against 20 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. value source note: THE DESCRIPTION DRAWS ON THE PAPER BEYOND THIS QUOTE: the VOC's 20 categories are stated just before ('VOC Dataset This dataset includes 20 object categories.').	`content_tags.quantities[0]`	0.95	the tagger's words
content_tags	the single IoU threshold behind AP50, the one COCO figure that is not averaged over a range Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`	0.95	the tagger's words
content_tags	average precision Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: average precision	`content_tags.statistics[0]`	0.95	the tagger's words
content_tags	precision Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: precision	`content_tags.statistics[1]`	0.95	the tagger's words
content_tags	recall Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: recall	`content_tags.statistics[2]`	0.95	the tagger's words
content_tags	confidence threshold Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: confidence threshold	`content_tags.variables[0]`	0.95	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.