Methods › General › Loss Functions › Varifocal Loss
Varifocal Loss
Introduced by Haoyang Zhang et al. in VarifocalNet: An IoU-aware Dense Object Detector
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Varifocal Loss is a loss function for training a dense object detector to predict the IACS, inspired by focal loss. Unlike the focal loss that deals with positives and negatives equally, Varifocal Loss treats them asymmetrically.
VFL(p, q) = −q(qlog(p) + (1 − q)log(1 − p)) if q > 0
VFL(p, q) = −αp^γlog(1-p)
where p is the predicted IACS and q is the target IoU score.
For a positive training example, q is set as the IoU between the generated bounding box and the ground-truth one (gt IoU), whereas for a negative training example, the training target q for all classes is 0.
In Syntology for a different name, 'Varifocal', about another paper, arXiv:2210.12400: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Varifocal' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2210.12400, while the archive credits arXiv:2008.13367.
Origin paper of this answer, arXiv:2210.12400 (its page on this site · its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 8 · with a code link: 4 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 8 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 8 of 8, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT 8 Apr 2025 · 0 repositories · arXiv:2504.05591
-
Universal Lymph Node Detection in Multiparametric MRI with Selective Augmentation 7 Apr 2025 · 0 repositories · arXiv:2504.05196
-
Comparing Surface Landmine Object Detection Models on a New Drone Flyby Dataset 17 Oct 2024 · 0 repositories · arXiv:2410.19807
-
How to Train an Accurate and Efficient Object Detection Model on Any Dataset 30 Nov 2022 · 1 repository · arXiv:2211.17170
-
Universal Lymph Node Detection in T2 MRI using Neural Networks 31 Mar 2022 · 0 repositories · arXiv:2204.00622
-
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection 14 Feb 2022 · 6 repositories · arXiv:2202.06934Syntology official (archive's flag): 2 ran · 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 19 harvested samples)
-
SWA Object Detection 23 Dec 2020 · 2 repositories · arXiv:2012.12645
-
VarifocalNet: An IoU-aware Dense Object Detector 31 Aug 2020 · 4 repositories · arXiv:2008.13367Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
12 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Object Detection | 5 |
| object-detection | 4 |
| Object | 3 |
| Sensitivity | 2 |
| CPU | 1 |
| General Classification | 1 |
| Instance Segmentation | 1 |
| Landmine | 1 |
| Lesion Detection | 1 |
| Semantic Segmentation | 1 |
| Small Object Detection | 1 |
| TAG | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections