Deep Embedding using Bayesian Risk Minimization with Application to Sketch Recognition
arXiv:1812.02466
Abstract
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.
arXiv commentAccepted at ACCV 2018
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Survey on Metric Learning for Feature Vectors and Structured Data
- Learning Deep Embeddings with Histogram Loss
- SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
- Training-Free Synthesized Face Sketch Recognition Using Image Quality Assessment Metrics