Classification of Occluded Objects using Fast Recurrent Processing
This addresses the challenge of real-time object classification under occlusion for computer vision applications, though it appears incremental as it builds on existing recurrent and feedforward methods.
The paper tackles the problem of classifying occluded objects in computer vision by proposing a framework that integrates recurrent processing into feedforward networks to improve computational efficiency, achieving a 2× improvement in classification accuracy for occluded objects.
Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset, and shown to achieve 2$\times$ improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.