Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion

By Adam Kortylewski, Qing Liu, Huiyu Wang, Zhishuai Zhang, Alan L. Yuille. 2019

74 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Alan L. Yuille
  2. Qing Liu
  3. Adam Kortylewski
  4. Yihong Sun
  5. Angtian Wang
  6. Quoc V. Le
  7. Trevor Darrell
  8. Liang-Chieh Chen

In Computer Vision and Pattern Recognition

  1. Qing Liu
  2. Adam Kortylewski
  3. Alan L. Yuille
  4. Yihong Sun
  5. Angtian Wang
  6. Luc Van Gool
  7. Xiaogang Wang
  8. Iasonas Kokkinos

In Model Architectures

  1. Alan L. Yuille
  2. Qing Liu
  3. Yihong Sun
  4. Adam Kortylewski
  5. Angtian Wang
  6. Juergen Gall
  7. Xiaogang Wang
  8. Wanli Ouyang

Citations in the corpus