StampNet: unsupervised multi-class object discovery
arXiv:1902.02693 · doi:10.1109/ICIP.2019.8803767
Abstract
Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the location of the objects are not known: this adds additional degrees of freedom and increases the problem complexity. In this work, we propose StampNet, a novel autoencoding neural network that localizes shapes (objects) over a simple background in images and categorizes them simultaneously. StampNet consists of a discrete latent space that is used to categorize objects and to determine the location of the objects. The object categories are formed during the training, resulting in the discovery of a fixed set of objects. We present a set of experiments that demonstrate that StampNet is able to localize and cluster multiple overlapping shapes with varying complexity including the digits from the MNIST dataset. We also present an application of StampNet in the localization of pedestrians in overhead depth-maps.
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- Categorical Reparameterization with Gumbel-Softmax
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Recurrent Models of Visual Attention
- DRAW: A Recurrent Neural Network For Image Generation
- Recurrent Spatial Transformer Networks
- A large-scale real-life crowd steering experiment via arrow-like stimuli