Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion
- 1 March 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1322-1330
Abstract
Deep convolutional neural networks (DCNNs) are powerful models that yield impressive results at object classification. However, recent work has shown that they do not generalize well to partially occluded objects and to mask attacks. In contrast to DCNNs, compositional models are robust to partial occlusion, however, they are not as discriminative as deep models. In this work, we combine DC-NNs and compositional object models to retain the best of both approaches: a discriminative model that is robust to partial occlusion and mask attacks. Our model is learned in two steps. First, a standard DCNN is trained for image classification. Subsequently, we cluster the DCNN features into dictionaries. We show that the dictionary components resemble object part detectors and learn the spatial distribution of parts for each object class. We propose mixtures of compositional models to account for large changes in the spatial activation patterns (e.g. due to changes in the 3D pose of an object). At runtime, an image is first classified by the DCNN in a feedforward manner. The prediction uncertainty is used to detect partially occluded objects, which in turn are classified by the compositional model. Our experimental results demonstrate that combining compositional models and DCNNs resolves a fundamental problem of current deep learning approaches to computer vision: The combined model recognizes occluded objects, even when it has not been exposed to occluded objects during training, while at the same time maintaining high discriminative performance for non-occluded objects.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Interpretable Convolutional Neural Networks2018
- A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAsScience, 2017
- Towards deep compositional networks2016
- Deep Residual Learning for Image Recognition2016
- Probabilistic Compositional Active Basis Models for Robust Pattern Recognition2016
- Unsupervised Learning of Dictionaries of Hierarchical Compositional Models2014
- Beyond PASCAL: A benchmark for 3D object detection in the wild2014
- ImageNet: A large-scale hierarchical image database2009
- Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion2008
- Context and Hierarchy in a Probabilistic Image Model2006