Adaptive and Iteratively Improving Recurrent Lateral Connections
arXiv:1910.11105
Abstract
The current leading computer vision models are typically feed forward neural models, in which the output of one computational block is passed to the next one sequentially. This is in sharp contrast to the organization of the primate visual cortex, in which feedback and lateral connections are abundant. In this work, we propose a computational model for the role of lateral connections in a given block, in which the weights of the block vary dynamically as a function of its activations, and the input from the upstream blocks is iteratively reintroduced. We demonstrate how this novel architectural modification can lead to sizable gains in performance, when applied to visual action recognition without pretraining and that it outperforms the literature architectures with recurrent feedback processing on ImageNet.
References in corpus (15)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Two-Stream Convolutional Networks for Action Recognition in Videos
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- The Kinetics Human Action Video Dataset
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex
- Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
- Long-term Temporal Convolutions for Action Recognition
- Attention for Fine-Grained Categorization
- Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
- Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
- Detecting Visual Relationships with Deep Relational Networks
- IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
- Video Action Recognition Via Neural Architecture Searching
- Spatio-Temporal Channel Correlation Networks for Action Classification