Claims › ext:85a7fe26510c242b › line of work
Its line of work
YOLOv4-large model achieves state-of-the-art results: 55.5% AP (73.4% AP50) for the MS COCO dataset at a speed of ~16 FPS on Tesla V100, while with the test time augmentation, YOLOv4-large achieves 56.0% AP (73.3 AP50).
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.
● 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 14.3 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 | Use | Stakes | Rests on |
|---|---|---|---|---|---|---|
| Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up p… | ○ unchecked | yes | 0.55 | 0 | 10.9 | — |
| YOLOv4-large model achieves state-of-the-art results: 55.5% AP (73.4% AP50) for the MS COCO dataset at a speed of ~16 F… | ○ unchecked | yes | 0.55 | 0 | 10.7 | Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up p…, We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, an… |
| We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, an… | ○ unchecked | yes | 0.55 | 0 | 14.3 | Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up p… |
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 | Specifically, we enhance the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the inf…this claim takes its method from it, as the citing paper says · human literature · ext:076edde17134ec3a | 0.55 |
| 1 step below | unchecked | We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to…this claim extends it, as the citing paper says · human literature · ext:b27a5da54b02ef96 | 0.55 |
| this claim | unchecked | YOLOv4-large model achieves state-of-the-art results: 55.5% AP (73.4% AP50) for the MS COCO dataset at a speed of ~16 FPS on Tesla V100, while with the test ti…human literature · ext:85a7fe26510c242b | 0.55 |
Background mentions carry no weight and are not part of the line. Every number recomputes from the public log.