Understanding the Effective Receptive Field in Deep Convolutional Neural Networks¶
Luo, W., Li, Y., Urtasun, R., & Zemel, R. (2016). Understanding the Effective Receptive Field in Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Receptive Field
- Convolutional neural networks: each filter responds to a local input patch, deeper layers build larger effective receptive fields by composition, and field size is a primary design parameter computable in advance from kernel, stride, dilation, and depth.
This sourceShows the effective receptive field is Gaussian and a fraction of the theoretical field, growing with depth and computable from kernel, stride, dilation, and depth.
- Convolutional neural networks: each filter responds to a local input patch, deeper layers build larger effective receptive fields by composition, and field size is a primary design parameter computable in advance from kernel, stride, dilation, and depth.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:49a21ccbe689 · see in the full table