Methods › Computer Vision › Convolutions › CondConv
CondConv
Introduced by Brandon Yang et al. in CondConv: Conditionally Parameterized Convolutions for Efficient Inference
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
CondConv, or Conditionally Parameterized Convolutions, are a type of convolution which learn specialized convolutional kernels for each example. In particular, we parameterize the convolutional kernels in a CondConv layer as a linear combination of n experts (α₁ W₁ + …+ αₙ Wₙ) * x, where α₁, …, αₙ are functions of the input learned through gradient descent. To efficiently increase the capacity of a CondConv layer, developers can increase the number of experts. This can be more computationally efficient than increasing the size of the convolutional kernel itself, because the convolutional kernel is applied at many different positions within the input, while the experts are combined only once per input.
Papers archive 2025-07-28
5 shown of 5, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Frequency Dynamic Convolution for Dense Image Prediction 24 Mar 2025 · 1 repository · arXiv:2503.18783Syntology ran 0 of 2 samples · 2 unverified
-
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs 8 Jul 2021 · 0 repositories · arXiv:2107.03815
-
EXTENDING CONDITIONAL CONVOLUTION STRUCTURES FOR ENHANCING MULTITASKING CONTINUAL LEARNING 7 Dec 2020 · 1 repository
-
WeightNet: Revisiting the Design Space of Weight Networks 23 Jul 2020 · 2 repositories · arXiv:2007.11823Syntology ran 1 of 1 samples · 0 unverified
-
CondConv: Conditionally Parameterized Convolutions for Efficient Inference 10 Apr 2019 · 9 repositories · arXiv:1904.04971
Tasks archive 2025-07-28
8 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 |
|---|---|
| Image Classification | 2 |
| Object Detection | 2 |
| Computational Efficiency | 1 |
| Continual Learning | 1 |
| General Classification | 1 |
| Multi-Task Learning | 1 |
| Prediction | 1 |
| object-detection | 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