A Deep Learning Framework for Authorship Classification of Paintings

Similar documents
Large-scale Video Classification with Convolutional Neural Networks

Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks

TRANSPARENT OBJECT DETECTION USING REGIONS WITH CONVOLUTIONAL NEURAL NETWORK

Yiqi Yan. May 10, 2017

A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS. Kuan-Chuan Peng and Tsuhan Chen

Semantic Segmentation

Deep Neural Networks:

Multi-Glance Attention Models For Image Classification

Convolutional Neural Networks

Deep Learning with Tensorflow AlexNet

Know your data - many types of networks

DeepIndex for Accurate and Efficient Image Retrieval

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech

Fully Convolutional Networks for Semantic Segmentation

Spatial Localization and Detection. Lecture 8-1

Extend the shallow part of Single Shot MultiBox Detector via Convolutional Neural Network

Regionlet Object Detector with Hand-crafted and CNN Feature

CS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016

Return of the Devil in the Details: Delving Deep into Convolutional Nets

Rich feature hierarchies for accurate object detection and semantic segmentation

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro

CS230: Lecture 3 Various Deep Learning Topics

DEEP NEURAL NETWORKS FOR OBJECT DETECTION

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification

CS 523: Multimedia Systems

Object Recognition II

INF 5860 Machine learning for image classification. Lecture 11: Visualization Anne Solberg April 4, 2018

Image Transformation via Neural Network Inversion

Su et al. Shape Descriptors - III

Transfer Learning. Style Transfer in Deep Learning

Deep Learning. Deep Learning. Practical Application Automatically Adding Sounds To Silent Movies

CPSC340. State-of-the-art Neural Networks. Nando de Freitas November, 2012 University of British Columbia

Object detection using Region Proposals (RCNN) Ernest Cheung COMP Presentation

Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization. Presented by: Karen Lucknavalai and Alexandr Kuznetsov

Convolutional-Recursive Deep Learning for 3D Object Classification

CS 1674: Intro to Computer Vision. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 16, 2016

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. By Joa õ Carreira and Andrew Zisserman Presenter: Zhisheng Huang 03/02/2018

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs

CEA LIST s participation to the Scalable Concept Image Annotation task of ImageCLEF 2015

Two-Stream Convolutional Networks for Action Recognition in Videos

Machine Learning. MGS Lecture 3: Deep Learning

Computer Vision Lecture 16

Intro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn

Multi-resolution-Tract CNN with Hybrid Pretrained and Skin-Lesion Trained Layers

Object Detection on Self-Driving Cars in China. Lingyun Li

ConvolutionalNN's... ConvNet's... deep learnig

What was Monet seeing while painting? Translating artworks to photo-realistic images M. Tomei, L. Baraldi, M. Cornia, R. Cucchiara

A Deep Learning primer

Using Machine Learning for Classification of Cancer Cells

Pouya Kousha Fall 2018 CSE 5194 Prof. DK Panda

DEEP LEARNING REVIEW. Yann LeCun, Yoshua Bengio & Geoffrey Hinton Nature Presented by Divya Chitimalla

Towards Large-Scale Semantic Representations for Actionable Exploitation. Prof. Trevor Darrell UC Berkeley

Deep learning for dense per-pixel prediction. Chunhua Shen The University of Adelaide, Australia

Fully-Convolutional Siamese Networks for Object Tracking

Volumetric and Multi-View CNNs for Object Classification on 3D Data Supplementary Material

Fine-tuning Pre-trained Large Scaled ImageNet model on smaller dataset for Detection task

Deep Learning in Pulmonary Image Analysis with Incomplete Training Samples

Object detection with CNNs

Rotation Invariance Neural Network

Deep Learning in Visual Recognition. Thanks Da Zhang for the slides

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling

Recognize Complex Events from Static Images by Fusing Deep Channels Supplementary Materials

Object Detection Based on Deep Learning

INTRODUCTION TO DEEP LEARNING

Dynamic Routing Between Capsules

CS231N Project Final Report - Fast Mixed Style Transfer

Part Localization by Exploiting Deep Convolutional Networks

Face Recognition A Deep Learning Approach

Recurrent Convolutional Neural Networks for Scene Labeling

Real-time Object Detection CS 229 Course Project

SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic

Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

Apparel Classifier and Recommender using Deep Learning

Proceedings of the International MultiConference of Engineers and Computer Scientists 2018 Vol I IMECS 2018, March 14-16, 2018, Hong Kong

Layerwise Interweaving Convolutional LSTM

Kaggle Data Science Bowl 2017 Technical Report

Deeply Cascaded Networks

COMP 551 Applied Machine Learning Lecture 16: Deep Learning

An Exploration of Computer Vision Techniques for Bird Species Classification

END-TO-END CHINESE TEXT RECOGNITION

COMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017

Machine Learning 13. week

Mask R-CNN. presented by Jiageng Zhang, Jingyao Zhan, Yunhan Ma

Optical flow. Cordelia Schmid

Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neural Networks

REGION AVERAGE POOLING FOR CONTEXT-AWARE OBJECT DETECTION

PIXELS TO VOXELS: MODELING VISUAL REPRESENTATION IN THE HUMAN BRAIN

Classification of objects from Video Data (Group 30)

Convolutional Neural Networks: Applications and a short timeline. 7th Deep Learning Meetup Kornel Kis Vienna,

Recurrent Neural Networks and Transfer Learning for Action Recognition

Deep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon

Deep Learning. Deep Learning provided breakthrough results in speech recognition and image classification. Why?

Neural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017

Lecture 7: Semantic Segmentation

Feature-Fused SSD: Fast Detection for Small Objects

CS6501: Deep Learning for Visual Recognition. Object Detection I: RCNN, Fast-RCNN, Faster-RCNN

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

Structured Prediction using Convolutional Neural Networks

Transcription:

A Deep Learning Framework for Authorship Classification of Paintings Kai-Lung Hua ( 花凱龍 ) Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei, Taiwan

Massive digitized painting images on the Internet Everyone can upload artworks.

Digitized painting images lack information. For example, authorship can determine era, place, media and style.

Why artist-based image classification? Facilitate artist-based retrieval Identify unknown paintings Provide insights from an artist s artwork

Challenges: Different artists may draw similar objects. An artist may have several techniques. Different artists may have similar techniques.

Methods

Deep Learning Using brain-inspired mechanics to achieve brain-like function [Ref] http://www.slideshare.net/roelofp/041114-dl-nlpwordembeddings

Different Levels of Abstraction

Traditional Learning Approach [Ref] http://slazebni.cs.illinois.edu/spring14/lec24_cnn.pdf

What about learning the features? Learn a feature hierarchy all the way from pixels to classifier Each layer extracts features from the output of previous layer Train all layers jointly

Shallow vs. Deep Architectures

Basic Neural Network [Ref] http://www.amax.com/blog/?p=804

Deep Neural Network

State-of-the-art Image Classification Caffe: A framework based on Convolutional Neural Network (CNN) Caffe framework: Y. Jia, et al, Caffe: convolutional architecture for fast feature embedding," ACM International Conference in Multimedia, 2014. Convolutional Neural network: Y. LeCun, et al, Backpropagation applied to hand-written zip code recognition, Neural Computing, 1989.

Caffe has a rigid architecture Only receive 227 x 227 size of image input Images have arbitrary sizes. Relax the rigidness Utilize spatial pyramid representation

Spatial Pyramid Representation A collection of orderless features computed over cells defined

Training of Multi-scale Networks Train a model for each layer Fine-tune pre-trained network Pre-trained network: A. Krizhevsky, et al. Imagenet classication with deep convolutional neural networks, NIPS, 2012.

Methods using Trained Networks 1. Single-scale with Hard Decision using fine-tuned Krizhevsky s CNN Method (Baseline) 2. Multi-scale Pyramid with Hard Decision 3. Multi-scale Pyramid with Soft Decision 4. Multi-scale Pyramid with Soft Decision and Adaptive Pooling 5. MRF Refining Scheme Baseline: A. Krizhevsky, et al. Imagenet classication with deep convolutional neural networks, NIPS, 2012. 11 of 33

1 Single-scale with Hard Decision using fine-tuned Krizhevsky s CNN Method (Baseline) Only use the 1 st layer Predict using Caffe framework Baseline: A. Krizhevsky, et al. Imagenet classication with deep convolutional neural networks, NIPS, 2012.

General Work Flow of Using Multi-scale Networks Work flow for the 2 nd, 3 rd and 4 th method

2 Multi-scale Pyramid with Hard Decision Method Obtain a predicted class label for each image patch from the model Use voting to pool the labels for each layer Combine the results of 3 layers using weights 16:4:1

3 Multi-scale Pyramid with Soft Decision Method Obtain a distribution over the classes for each image patch from the model Sum the probability values in each layer Combine 3 layers using weights 16:4:1

4 Multi-scale Pyramid with Soft Decision Method and Adaptive Pooling Combine 3 layers using adaptive weights based on class entropy

Adaptive Weights Entropy for the j-layer: (1) Weight for the j-layer: (2) Aggregation of 3 layers: (3) Choose the class with the maximum probability as the final decision

5 Markov Random Field (MRF) Refining Method Obtain a predicted class label for each image patch from the model Fuse patch-level results using MRF

MRF Refining Scheme Work Flow

MRF Refining Scheme Formula MRF energy function to predict a node as class i: (4) data. Data term Compute the compatibility of the labeling with the given (5) Smoothness term Penalize node that has different labeled neighbor. (6)

MRF Scheme: Combining Patch-level Results Convert hard into soft decision (7)

MRF Scheme: Combining Patch-level Results Layer Entropy: (8) Layer Weight: (9) Aggregate 3 layers using the adaptive weight method

EXPERIMENTS

Dataset PaintingDb dataset 1300 painting images of 13 artists (100 images / artist) WikiArt dataset 20405 painting images of 23 artists PaintingDb: PaintingDb, PaintingDb fastest growing art gallery in the web," 2015. www.paintingdb.com WikiArt: www.wikiart.org WikiArt, WikiArt the online home for visual arts from all around the world., 2016.

Experiment Setup Experiment 1 (PaintingDb dataset) 80 images for training, 20 images for testing (for each class) Experiment 2 (WikiArt dataset) 2/3 images for training, 1/3 images for testing (for each class) Measurements: precision, recall, and F-score.

Experiment 1: Contribution of Multi-scale Pyramid

Experiment 1: Result

Experiment 2: Result

Conclusion We address the painter classification problem using deep learning approaches. Experiments show our proposed methods that utilize multi-scale pyramid outperform the baseline method. In experiment 1, the MRF refining scheme can significantly boost the performance of Multi-scale pyramid with adaptive fusion.

Future Work A better fusion scheme that aggregates the results from different layers should be further investigated. An inspection of a good method for finding MRF parameters automatically.