Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification
arXiv:2101.03154
Abstract
Tiny object classification problem exists in many machine learning applications like medical imaging or remote sensing, where the object of interest usually occupies a small region of the whole image. It is challenging to design an efficient machine learning model with respect to tiny object of interest. Current neural network structures are unable to deal with tiny object efficiently because they are mainly developed for images featured by large scale objects. However, in quantum physics, there is a great theoretical foundation guiding us to analyze the target function for image classification regarding to specific objects size ratio. In our work, we apply Tensor Networks to solve this arising tough machine learning problem. First, we summarize the previous work that connects quantum spin model to image classification and bring the theory into the scenario of tiny object classification. Second, we propose using 2D multi-scale entanglement renormalization ansatz (MERA) to classify tiny objects in image. In the end, our experimental results indicate that tensor network models are effective for tiny object classification problem and potentially will beat state-of-the-art. Our codes will be available online https://github.com/timqqt/MERA_Image_Classification.
8 pages, 7 figures
References in corpus (8)
- Multiple Object Recognition with Visual Attention
- Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines
- TensorNetwork for Machine Learning
- Scaling of entanglement entropy in the (branching) multi-scale entanglement renormalization ansatz
- Entanglement Area Law for Shallow and Deep Quantum Neural Network States
- Tensor Networks for Medical Image Classification
- Needles in Haystacks: On Classifying Tiny Objects in Large Images
- Entanglement Entropy of Target Functions for Image Classification and Convolutional Neural Network