Attention Mechanisms for Object Recognition with Event-Based Cameras
arXiv:1807.09480
Abstract
Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power consumption benefits of biological vision. In this paper we focus on a specific feature of vision: visual attention. We propose two attentive models for event based vision: an algorithm that tracks events activity within the field of view to locate regions of interest and a fully-differentiable attention procedure based on DRAW neural model. We highlight the strengths and weaknesses of the proposed methods on four datasets, the Shifted N-MNIST, Shifted MNIST-DVS, CIFAR10-DVS and N-Caltech101 collections, using the Phased LSTM recognition network as a baseline reference model obtaining improvements in terms of both translation and scale invariance.
arXiv commentWACV2019 camera-ready submission
References in corpus (13)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Multi-Scale Context Aggregation by Dilated Convolutions
- Recurrent Models of Visual Attention
- DRAW: A Recurrent Neural Network For Image Generation
- Fully Convolutional Networks for Semantic Segmentation
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- Feature Pyramid Networks for Object Detection
- YOLO9000: Better, Faster, Stronger
- Aggregated Residual Transformations for Deep Neural Networks
- Residual Attention Network for Image Classification
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences
- SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning