Batch-Shaped Channel Gated Networks

By Babak Ehteshami Bejnordi, Tijmen Blankevoort, Max Welling. 2019

9 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yizeng Han
2. Tinne Tuytelaars
3. Shiji Song
4. Gao Huang
5. Gyuhak Kim
6. Luc Van Gool
7. Yi Yang
8. Yoshua Bengio

Citations in the corpus

• Conditional Channel Gated Networks for Task-Aware Continual Learning (2020, methodology): “Specifically, our framework relies on separate task-specific classification heads ( multi-head architecture), and it employs channel-gating [6, 3] in every layer of the (shared) feature extractor.”
• Resolution Adaptive Networks for Efficient Inference (2020, background): “Recent works also propose to adaptively skip layers or blocks [6, 36, 38, 39], or dynamically select channels [23, 3, 1] during inference time.”
• Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (2019, methodology): “[3] use the Gumbel-Softmax trick to gate channels conditionally on the input.”