论文信息 - MIML Learning with CNNs: Yelp Restaurant Photo Classification

MIML Learning with CNNs: Yelp Restaurant Photo Classification

We present the conditions of a data science challenge from Kaggle, which can be viewed as a multi-instance multilabel learning problem in the image domain, and describe the official training dataset provided. We discuss our technical approach, and address the challenges in using transfer learning and with finetuning, trying out different strategies to tackle the multi-instance aspect of the problem. Lastly, we present our results, and analyze in depth the quantitative and qualitative performance of our models.

Raghav Gupta | Pulkit Agrawal

[1] Iasonas Kokkinos,et al. Modeling local and global deformations in Deep Learning: Epitomic convolution, Multiple Instance Learning, and sliding window detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2] Eli Shechtman,et al. Yelp Restaurant Photo Classification , 2016 .

[3] Vasant Honavar,et al. Multi-Instance Multi-Label Learning for Image Classification with Large Vocabularies , 2011, BMVC.

[4] Jian Sun,et al. Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5] Andrew Zisserman,et al. Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[6] Gaël Varoquaux,et al. Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[7] Stefan Carlsson,et al. CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[8] Yoshua Bengio,et al. Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[9] Song Han,et al. A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman Encoding , 2015 .

[10] Zhi-Hua Zhou,et al. Multi-instance multi-label learning , 2008, Artif. Intell..