Unsupervised Learning using Pretrained CNN and Associative Memory Bank
This addresses the need for more efficient adaptation of pretrained models in general object recognition tasks, though it appears incremental as it builds on existing CNN and associative memory techniques.
The paper tackles the problem of time- and resource-consuming fine-tuning in pretrained CNN models by proposing an unsupervised object recognition approach that combines a pretrained CNN for feature extraction with a Hopfield network-based associative memory bank for classification, eliminating backpropagation and achieving competitive performance on unseen datasets.
Deep Convolutional features extracted from a comprehensive labeled dataset, contain substantial representations which could be effectively used in a new domain. Despite the fact that generic features achieved good results in many visual tasks, fine-tuning is required for pretrained deep CNN models to be more effective and provide state-of-the-art performance. Fine tuning using the backpropagation algorithm in a supervised setting, is a time and resource consuming process. In this paper, we present a new architecture and an approach for unsupervised object recognition that addresses the above mentioned problem with fine tuning associated with pretrained CNN-based supervised deep learning approaches while allowing automated feature extraction. Unlike existing works, our approach is applicable to general object recognition tasks. It uses a pretrained (on a related domain) CNN model for automated feature extraction pipelined with a Hopfield network based associative memory bank for storing patterns for classification purposes. The use of associative memory bank in our framework allows eliminating backpropagation while providing competitive performance on an unseen dataset.