On Learning Where To Look
arXiv:1405.5488
Abstract
Current automatic vision systems face two major challenges: scalability and extreme variability of appearance. First, the computational time required to process an image typically scales linearly with the number of pixels in the image, therefore limiting the resolution of input images to thumbnail size. Second, variability in appearance and pose of the objects constitute a major hurdle for robust recognition and detection. In this work, we propose a model that makes baby steps towards addressing these challenges. We describe a learning based method that recognizes objects through a series of glimpses. This system performs an amount of computation that scales with the complexity of the input rather than its number of pixels. Moreover, the proposed method is potentially more robust to changes in appearance since its parameters are learned in a data driven manner. Preliminary experiments on a handwritten dataset of digits demonstrate the computational advantages of this approach.
deep learning, vision
References in corpus (1)
Cited by in corpus (18)
- Recurrent Models of Visual Attention
- DRAW: A Recurrent Neural Network For Image Generation
- Deep neural network models for computational histopathology: A survey
- Learning to detect chest radiographs containing lung nodules using visual attention networks
- Attention for Fine-Grained Categorization
- Deep Reinforcement Learning for Visual Object Tracking in Videos
- Learning Generative Models with Visual Attention
- Seeing with Humans: Gaze-Assisted Neural Image Captioning
- Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
- Hard-Attention for Scalable Image Classification
- Towards Information-Seeking Agents
- Dynamic Capacity Networks
- Autonomous Curiosity for Real-Time Training Onboard Robotic Agents
- Pre-training Attention Mechanisms
- Visual Attention in Imaginative Agents
- Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks
- Learning Fixation Point Strategy for Object Detection and Classification
- Understanding top-down attention using task-oriented ablation design