Deep Embedding using Bayesian Risk Minimization with Application to Sketch Recognition
This addresses sketch recognition for applications like digital art or education, with incremental improvements over existing methods.
The paper tackles hand-drawn sketch recognition by introducing a deep metric learning loss based on Bayesian risk minimization to learn discriminative embeddings, achieving 82.2% and 88.7% accuracy on TU-Berlin-250 and TU-Berlin-160 benchmarks, respectively.
In this paper, we address the problem of hand-drawn sketch recognition. Inspired by the Bayesian decision theory, we present a deep metric learning loss with the objective to minimize the Bayesian risk of misclassification. We estimate this risk for every mini-batch during training, and learn robust deep embeddings by backpropagating it to a deep neural network in an end-to-end trainable paradigm. Our learnt embeddings are discriminative and robust despite of intra-class variations and inter-class similarities naturally present in hand-drawn sketch images. Outperforming the state of the art on sketch recognition, our method achieves 82.2% and 88.7% on TU-Berlin-250 and TU-Berlin-160 benchmarks respectively.