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¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:3e5677b33a72 · see in the full table