scholar.google.com › citations
In this paper, we formulate the dynamic routing problem from the perspective of feature compression and reconstruction, proposing a novel routing algorithm.
In this paper, we formulate the dynamic routing problem from the perspective of feature compression and reconstruction, proposing a novel routing algorithm ...
In this paper, we formulate the dynamic routing problem from the perspective of feature compression and reconstruction, proposing a novel routing algorithm ...
In this paper, we formulate the dynamic routing problem from the perspective of feature compression and reconstruction, proposing a novel routing algorithm ...
Garcia-Garcia, A survey on deep learning techniques for image and video semantic segmentation, Appl. Soft Comput., № 70, с. 41
Suofei Zhang, Wenhao Fan, Xiaofu Wu: Towards capsule routing as reconstruction with sparsity constraints. Pattern Recognit. Lett. 140: 193-199 (2020).
Oct 6, 2022 · Abstract. Capsule networks are a neural network architecture special- ized for visual scene recognition. Features and pose information are ...
In this paper, we propose an Orthogonal Capsule Network (OrthCaps) to reduce redundancy, improve routing performance and decrease parameter counts. Firstly, an ...
Missing: constraints. | Show results with:constraints.
This paper proposes a new routing method called CFR for filtering capsules based on capsule activation values, which can speed up the operation of the model ...
Sparse routing, A routing algorithm that selects a small subset of capsules to route information to the next layer based on a sparsity constraint. The ...