He, Zhang, Ren & Sun, "Deep Residual Learning for Image Recognition" (arXiv)

Kaiming He, Jian Sun · 10 Dec 2015 · arxiv.org ↗

8 korrents from this paper

In plain words

Making neural nets much deeper for image recognition works better if layers learn only the difference from their inputs instead of full new mappings, letting accuracy rise with depth. These let them build networks eight times deeper than earlier ones yet simpler, cutting error to 3.57 percent on a major image test and improving object spotting by 28 percent. It proposes a training method for very deep nets and reports the contest-winning image results that follow when depth is no longer so hard to optimize.

Our summary of the paper, not the authors' words — written to be readable without the field's vocabulary, from the stored copy of the paper and nothing else. Drafted with xai:grok-4.5 and checked by a person. The authors' own sentences are the quotes below.

Near this, by wording

Papers whose claims are worded most like this one's, found by the same hourly pass that draws the map. It is a measure of LANGUAGE, not of agreement or of citation: two papers can be near each other here and flatly contradict one another.

Kaiming He, Jian Sun did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
Depth is not free: past a point, deeper neural networks are harder to train rather than simply better.

Their wordsDeeper neural networks are more difficult to train.

Interesting
Our reading
Depth is not free: past a point, deeper neural networks are harder to train rather than simply better.

Their wordsDeeper neural networks are more difficult to train.

Interesting
Our reading
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.

Their wordsWe explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions.

Interesting
Our reading
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.

Their wordsWe explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions.

Interesting
Our reading
Residual networks are easier to optimize than plain ones and keep gaining accuracy as depth increases.

Their wordsWe provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Interesting
Our reading
Residual networks are easier to optimize than plain ones and keep gaining accuracy as depth increases.

Their wordsWe provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Interesting
Our reading
The depth of a representation, not any particular architecture trick, is what most visual recognition tasks turn on.

Their wordsThe depth of representations is of central importance for many visual recognition tasks.

Interesting
Our reading
The depth of a representation, not any particular architecture trick, is what most visual recognition tasks turn on.

Their wordsThe depth of representations is of central importance for many visual recognition tasks.

Interesting