U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger, Philipp Fischer, Thomas Brox · MICCAI / arXiv · 2015 · medicine · record ronneberger2015-unet
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. The 'contradicts' relation to Ciresan et al. [1] is a case against that approach (speed, and the localisation/context trade-off), not a contradiction of a factual claim; none of the four permitted types fits an 'our numbers beat theirs' comparison, which is why the challenge-table superiority claims are not encoded as relations. The paper states no limitation section of its own; the two limitations recorded are constraints it explicitly attributes to its own design. Sentences containing the loss and weight-map equations are mangled by PDF extraction and were avoided. 2026-08-14, 2026-08-15, 2026-08-16 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. Update, 15 September 2026: EXCEPTION, measured with the merge gate's own predicate (Paper.locate): 1 quote(s) on this record are not found as one exact string in the current staged text - content_tags.statistics[0].evidence. The sentence above does not hold for them as written. Where a row records why - the quote is grounded in another copy of the paper, joins two passages with an ellipsis, or differs from the staged text by extraction noise - that note stays on the row.

The quality of the text these quotes were cut from. symbol-font-not-extractable: 12 '(cid:NNN)' glyph-index markers remain in a staged text of 17,221 characters, where the PDF's embedded font had no ToUnicode map. THE QUOTES ON THIS RECORD ARE THE PAPER'S AND THE STAGED COPY IS THE DAMAGED ONE - which is the opposite of the usual case and is why it went unnoticed: one of its 46 live quotes is not an exact substring of this text, and it was located in it by aligning the quote's WORD SEQUENCE under exactly this damage - the words are there, the characters inside them are not. Not repaired in place: editing the staged text moves every offset after the edit and re-hashes every anchor on the record. Measured at 113aae60fefc3eb1, re-measured unchanged at 54b63482778ddf56.

1 quote on this page breaks a word across a line. The PDF this text was extracted from hyphenated a word at the end of a printed line — adversar- ial, repre- sentations — and the extractor kept the hyphen and the space. The quotes keep them because a quote is reproduced exactly or it proves nothing: the break is the typesetter’s, not the author’s. A search of this page will not find the affected words.

1 quote on this page was cut from a different copy of this article. This project holds two extractions of this paper: the plain text every other quote here is anchored in, and the publisher’s own HTML edition, which we are not licensed to republish. It is verbatim in the second and cannot be found in the first — not because the tagging is wrong, but because the extraction damaged the passage: a page number dropped into the middle of a number, a formula moved out of its sentence, a ligature where two letters belong. The record names the copy for each one. The quote is the paper’s; the extraction is not.

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
training 3 fields · standard-deviation 3 fields · data augmentation 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.

image segmentation U-Net convolutional network biomedical imaging data augmentation elastic deformations invariance weight map separation border overlap-tile prediction with mirrored extrapolation at the border: the missing context outside the image is manufactured by reflecting the image itself, so a tile can be segmented without the network ever seeing beyond the edge elastic deformation of the training images, generated from random displacement vectors on a coarse 3 by 3 grid, sampled from a Gaussian with 10 pixels standard deviation and interpolated to per-pixel displacements with bicubic interpolation a per-pixel loss weight, pre-computed from each ground truth segmentation by morphological operations, that both compensates class frequency and forces the network to learn the small separation borders introduced between touching cells a large number of feature channels in the expansive path, which is what carries context from the contracting path up into the high-resolution layers and makes the architecture symmetric batch size traded down to a single image so the input tile can be large, with the momentum raised to 0.99 so that the update still integrates many previously seen samples initial weights drawn so that each feature map starts at approximately unit variance, which is what stops one path through the network from saturating while another never contributes network segmentation images training convolutional localization augmentation pixel architecture contracting path expanding path annotated samples class label standard-deviation standard deviation 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
transfer	`transfers`	a method or concept carried in from another field

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/1505.04597. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 5 · claim_type 1 · concept_edges 2 · concepts 5 · content_tags 9 · controls 1 · limitations 5 · mechanisms 6 · method 1 · phenomenon 1 · senses 3 · transfers 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; 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	biomedical image segmentation 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: overlap-tile prediction with mirrored extrapolation at the border: the missing context outside the image is manufactured by reflecting the image itself, so a tile can be segmented without the network ever seeing beyond the edge	`mechanisms[0]`	0.9	the tagger's words
mechanisms	the paper's claim that this teaches invariance WITHOUT annotating the transformations is made in the introduction, not in this span; tagged separately or not at all Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: elastic deformation of the training images, generated from random displacement vectors on a coarse 3 by 3 grid, sampled from a Gaussian with 10 pixels standard deviation and interpolated to per-pixel displacements with bicubic interpolation	`mechanisms[1]`	0.9	the tagger's words
mechanisms	the size of that weight - w0 = 10 - is stated in a different sentence and is not claimed here Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: a per-pixel loss weight, pre-computed from each ground truth segmentation by morphological operations, that both compensates class frequency and forces the network to learn the small separation borders introduced between touching cells	`mechanisms[2]`	0.9	the tagger'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: a large number of feature channels in the expansive path, which is what carries context from the contracting path up into the high-resolution layers and makes the architecture symmetric	`mechanisms[3]`	0.9	the tagger'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: batch size traded down to a single image so the input tile can be large, with the momentum raised to 0.99 so that the update still integrates many previously seen samples	`mechanisms[4]`	0.9	the tagger'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: initial weights drawn so that each feature map starts at approximately unit variance, which is what stops one path through the network from saturating while another never contributes	`mechanisms[5]`	0.9	the tagger's words
limitations	Because convolutions are unpadded, border pixels are lost at every layer and feature maps must be cropped before concatenation. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: every output map's extent relative to its input: THE CROPPING IS NECESSARY DUE TO THE LOSS OF BORDER PIXELS IN EVERY CONVOLUTION	`limitations[0]`		the tagger's words
limitations	Without the overlap-tile strategy the resolution the network can handle is bounded by GPU memory. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: application to large images: THIS TILING STRATEGY IS IMPORTANT ... SINCE OTHERWISE THE RESOLUTION WOULD BE LIMITED BY THE GPU MEMORY	`limitations[1]`		the tagger's words
limitations	Part of what the network is trained to detect is inserted by the authors: the separation borders between touching cells are synthesised, not annotated. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: a comparison of this network's boundary accuracy against a method trained on unmodified ground truth: the separation borders between touching cells are introduced by the authors and computed with morphological operations, so the two are trained on different targets	`limitations[2]`	1.0	the tagger's words
limitations	How heavily those borders count is set by two chosen constants in the loss. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the segmentation scores reported here: the pixel-wise loss weight that forces border learning is controlled by two values the authors chose, w0 = 10 and a sigma of about 5 pixels	`limitations[3]`	1.0	the tagger's words
limitations	The invariances the network has are the ones the augmentation supplied, and the paper says the corpus never contained them. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: a claim that this network is robust to deformation: the invariance was taught by applying elastic deformations during training, and the paper states the annotated corpus did not need to contain those transformations at all	`limitations[4]`	1.0	the tagger's words
transfers	convolutional networks applied to biomedical image segmentation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
controls	evaluation on a public challenge test set whose segmentation maps are kept secret by the organisers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: tuning against the test labels - the authors could not have done it even had they wanted to, which is a stronger guarantee than any promise a paper makes about itself · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.85	the tagger's words
concepts	data augmentation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data augmentation	`concepts[4]`		the paper's words
concepts	elastic deformations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: elastic deformations	`concepts[5]`		the paper's words
concepts	invariance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: invariance	`concepts[6]`		the paper's words
concepts	weight map Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: weight map	`concepts[7]`		the paper's words
concepts	separation border Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: separation border	`concepts[8]`		the paper's words
senses	the ground truth - PARTLY SYNTHESISED: the annotation is augmented with separation borders computed by morphological operations so that touching instances can be pulled apart, so the target is the annotation plus an artefact of the method 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	very few images - AS THIRTY, AND THEN AS PATCHES: the electron-microscopy training set is 30 images, and the paper notes that in patches the training data is much larger than the image count suggests 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	invariance - AS A PROPERTY OF THE AUGMENTATION: what the network is invariant to is what was applied to the training images, not what was observed in the microscopy 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 → sliding-window convolutional networks 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	contradicts → the assumption that deep networks need thousands of annotated samples 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	builds-on → the fully convolutional network of Long et al. [9] 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 → the fully convolutional network of Long et al. [9] 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
claim_relations	contradicts → the sliding-window patch strategy of Ciresan et al. [1] Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[4]`		the tagger's words
concept_edges	elastic deformations —causes→ invariance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but endpoint by anaphora: 'This allows' = the augmentation by elastic deformations (previous sentence). also in: elastic deformations · invariance	`concept_edges[0]`		the tagger's words
concept_edges	EVIDENCE CORRECTED (RE-GROUNDED) · weight map —causes→ separation border Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. EVIDENCE CORRECTED: RE-GROUNDED. The old span named only 'separation border'. This sentence names both and states the mechanism: the weight map is pre-computed IN ORDER TO force the network to learn the separation borders. — strength of the relation: 1 Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says the weight map forces the network to learn the separation borders; causes is loose. also in: weight map · separation border	`concept_edges[1]`		the tagger's words
content_tags	30 — training set size for the ISBI EM segmentation task 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	7 — test-time averaging over rotated inputs 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	A contracting path captures context and a symmetric expanding path enables precise localization. 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	U-Net won the ISBI cell tracking challenge 2015 in these categories by a large margin. 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[1]`		the tagger's words
content_tags	annotated samples Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: annotated samples	`content_tags.variables[0]`		the tagger's words
content_tags	class label Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: class label	`content_tags.variables[1]`		the tagger's words
content_tags	data augmentation 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. also in: data augmentation	`content_tags.definitions[1]`		the tagger's words
content_tags	contracting path Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: contracting path	`content_tags.definitions[2]`		the tagger's words
content_tags	expanding path Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: expanding path	`content_tags.definitions[3]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

content_tags.statistics[0] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.

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.