Impostor Networks for Fast Fine-Grained Recognition

Abstract

In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-grained applications on low-power and non-GPU enabled platforms. Impostor networks compensate for the lightness of its `backend' network by combining it with a lightweight non-parametric classifier. The combination of a convolutional network and such non-parametric classifier is trained in an end-to-end fashion. Similarly to convolutional neural networks, impostor networks can fit large-scale training datasets very well, while also being able to generalize to new data points. At the same time, the bulk of computations within impostor networks happen through nearest neighbor search in high-dimensions. Such search can be performed efficiently on a variety of architectures including standard CPUs, where deep convolutional networks are inefficient. In a series of experiments with three fine-grained datasets, we show that impostor networks are able to boost the classification accuracy of a moderate-sized convolutional network considerably at a very small computational cost.

References in corpus (7)

• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• On Calibration of Modern Neural Networks
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Learning Structured Sparsity in Deep Neural Networks
• No Fuss Distance Metric Learning using Proxies
• The iNaturalist Species Classification and Detection Dataset

Cited by in corpus (1)

• Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring