Dynamic Zoom-in Network for Fast Object Detection in Large Images
arXiv:1711.05187
Abstract
We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detection progresses in a coarse-to-fine manner, first on a down-sampled version of the image and then on a sequence of higher resolution regions identified as likely to improve the detection accuracy. Built upon reinforcement learning, our approach consists of a model (R-net) that uses coarse detection results to predict the potential accuracy gain for analyzing a region at a higher resolution and another model (Q-net) that sequentially selects regions to zoom in. Experiments on the Caltech Pedestrians dataset show that our approach reduces the number of processed pixels by over 50% without a drop in detection accuracy. The merits of our approach become more significant on a high resolution test set collected from YFCC100M dataset, where our approach maintains high detection performance while reducing the number of processed pixels by about 70% and the detection time by over 50%.
arXiv commentCVPR2018
References in corpus (10)
- Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
- Multiple Object Recognition with Visual Attention
- YOLO9000: Better, Faster, Stronger
- Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
- Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
- NISP: Pruning Networks using Neuron Importance Score Propagation
- Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
- Adaptive Object Detection Using Adjacency and Zoom Prediction
- The Role of Context Selection in Object Detection
- C-WSL: Count-guided Weakly Supervised Localization
Cited by in corpus (5)
- Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
- Learning Rich Features for Image Manipulation Detection
- Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
- LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
- Deep Regionlets for Object Detection