Methods › General › Loss Functions › Seesaw Loss
Seesaw Loss
Introduced by Jiaqi Wang et al. in Seesaw Loss for Long-Tailed Instance Segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Seesaw Loss is a loss function for long-tailed instance segmentation. It dynamically re-balances the gradients of positive and negative samples on a tail class with two complementary factors: mitigation factor and compensation factor. The mitigation factor reduces punishments to tail categories w.r.t the ratio of cumulative training instances between different categories. Meanwhile, the compensation factor increases the penalty of misclassified instances to avoid false positives of tail categories. The synergy of the two factors enables Seesaw Loss to mitigate the overwhelming punishments on tail classes as well as compensate for the risk of misclassification caused by diminished penalties.
L_(seesaw)(x) = - ∑^Cᵢ₌₁yᵢlog(σ̂ᵢ)
with σ̂ᵢ̂ = (e^(zᵢ))/(- ∑^C_(j≠1)𝒮ᵢⱼe^(zⱼ)+e^(zᵢ))
Here 𝒮ᵢⱼ works as a tunable balancing factor between different classes. By a careful design of 𝒮ᵢⱼ, Seesaw loss adjusts the punishments on class j from positive samples of class i. Seesaw loss determines 𝒮ᵢⱼ by a mitigation factor and a compensation factor, as:
𝒮ᵢⱼ =ℳᵢⱼ · 𝒞ᵢⱼ
The mitigation factor ℳᵢⱼ decreases the penalty on tail class j according to a ratio of instance numbers between tail class j and head class i. The compensation factor 𝒞ᵢⱼ increases the penalty on class j whenever an instance of class i is misclassified to class j.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
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: 3 · with a code link: 2 · where Syntology ran a sample: 0 (0 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: none of the 3 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 3 of 3, 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.
-
Underwater Soft Coral Detection: SCoralNet for Accurate and Efficient Annotation. 1 Aug 2024 · 0 repositories
-
Watch out Venomous Snake Species: A Solution to SnakeCLEF2023 19 Jul 2023 · 1 repository · arXiv:2307.09748
-
Seesaw Loss for Long-Tailed Instance Segmentation 23 Aug 2020 · 5 repositories · arXiv:2008.10032
Tasks archive 2025-07-28
4 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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