Gather-excite: Exploiting feature context in convolutional neural networks
While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better cont...
Main Authors: | Hu, J, Shen, L, Albanie, S, Sun, G, Vedaldi, A |
---|---|
Format: | Conference item |
Published: |
Neural Information Processing Systems (NIPS) Foundation
2018
|
Similar Items
-
Semi-convolutional operators for instance segmentation
by: Novotny, D, et al.
Published: (2018) -
Exploiting the Use of Convolutional Neural Networks for Localization in Indoor Environments
by: Bruno V. Ferreira, et al.
Published: (2017-03-01) -
Visualizing deep convolutional neural networks using natural pre-images
by: Mahendran, A, et al.
Published: (2016) -
Speeding up convolutional neural networks with low rank expansions
by: Jaderberg, M, et al.
Published: (2014) -
Sign language segmentation with temporal convolutional networks
by: Renz, K, et al.
Published: (2021)