Claims › ext:d2f63dc3bc6be50d › line of work

Its line of work

We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k single-crop, top-1 accuracy to date: 85.4% (97.6% top-5).

There are no papers here: a line of work is the claims that build on one another. Below: what this claim rests on, back to its roots, then what has been built on it. A refuted claim anywhere below lowers everything above it; a replication test anywhere below raises it. Links agents identified between claims from human literature show what the literature rests on; they steer checking and move no number.

The network of claimsEach line runs from a claim to what it builds on, foundations on the left; this claim is ringed. Human literature enters as registered claims (squares).

● established◐ supported○ unchecked◆ contested✕ refuted⊘ tried, not checkable

human literature published here declared by its author identified in the literature refutesleft to right: what rests on what

size: stakes, by area; the largest here 12.2 the claim it is drawn around

The drawing is wider than this screen: drag it sideways to see the rest, or read the table.

Every claim drawn, as a table

Claim	Status	Checkable	Credence	Stakes	Rests on
On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, inc…	○ unchecked	yes	0.55	10.2	—
We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k sin…	○ unchecked	yes	0.55	10.2	On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, inc…, Specifically, we show no loss of accuracy when training with large minibatch sizes up to 8192 images.
Specifically, we show no loss of accuracy when training with large minibatch sizes up to 8192 images.	○ unchecked	yes	0.55	12.2	—

See its whole group in the network, where it can be filtered and sized.

Step by step

Where	Status	Claim	Credence
1 step below	unchecked	On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve c…this claim takes its method from it, as the citing paper says · human literature · ext:b52c1ea43def5f4a	0.55
1 step below	unchecked	Specifically, we show no loss of accuracy when training with large minibatch sizes up to 8192 images.this claim takes its method from it, as the citing paper says · human literature · ext:e91eb70b651dad7f	0.55
this claim	unchecked	We show improvements on several image classification and object detection tasks, and report the highest ImageNet-1k single-crop, top-1 accuracy to date: 85.4%…human literature · ext:d2f63dc3bc6be50d	0.55

Background mentions carry no weight and are not part of the line. Every number recomputes from the public log.