Claims › ext:3a1c339868af79f3 › line of work
Its line of work
With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler.
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 12.8 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 |
|---|---|---|---|---|---|---|
| Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives f… | ○ unchecked | yes | 0.55 | 0 | 11.8 | — |
| With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with sing… | ○ unchecked | yes | 0.55 | 0 | 12.8 | Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives f… |
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 | Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during tra…this claim takes its method from it, as the citing paper says · human literature · ext:1ea2b3b97054dd90 | 0.55 |
| this claim | unchecked | With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpa…human literature · ext:3a1c339868af79f3 | 0.55 |
Background mentions carry no weight and are not part of the line. Every number recomputes from the public log.