Focal Loss for Dense Object Detection¶
Lin, T., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2980-2988.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Majority-Dominated Aggregate Objective
- The four-move repair kit reads off the structure: reweight (cost-sensitive loss, focal loss, up-weighting positive terms), retune (move the decision threshold toward the minority), replace the metric (optimise per-class recall, not aggregate accuracy), or supplement (a separate minority-specific accountability layer).
This sourceIntroduces focal loss, down-weighting easy majority examples so the objective's gradient attends to the rare, hard minority class.
- The four-move repair kit reads off the structure: reweight (cost-sensitive loss, focal loss, up-weighting positive terms), retune (move the decision threshold toward the minority), replace the metric (optimise per-class recall, not aggregate accuracy), or supplement (a separate minority-specific accountability layer).
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:3e5677b33a72 · see in the full table