论文信息 - Using very deep autoencoders for content-based image retrieval

Using very deep autoencoders for content-based image retrieval

We show how to learn many layers of features on color images and we use these features to initialize deep autoencoders. We then use the autoencoders to map images to short binary codes. Using semantic hashing [6], 28-bit codes can be used to retrieve images that are similar to a query image in a time that is independent of the size of the database. This extremely fast retrieval makes it possible to search using multiple di erent transformations of the query image. 256-bit binary codes allow much more accurate matching and can be used to prune the set of images found using the 28-bit codes.

Geoffrey E. Hinton | Alex Krizhevsky | A. Krizhevsky

[1] Geoffrey E. Hinton,et al. Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[2] Yee Whye Teh,et al. A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[3] Geoffrey E. Hinton,et al. Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure , 2007, AISTATS.

[4] Antonio Torralba,et al. Ieee Transactions on Pattern Analysis and Machine Intelligence 1 80 Million Tiny Images: a Large Dataset for Non-parametric Object and Scene Recognition , 2022 .

[5] Antonio Torralba,et al. Spectral Hashing , 2008, NIPS.

[6] Antonio Torralba,et al. Small codes and large image databases for recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7] Geoffrey E. Hinton. Reducing the Dimensionality of Data with Neural , 2008 .

[8] Alex Krizhevsky,et al. Learning Multiple Layers of Features from Tiny Images , 2009 .

[9] Geoffrey E. Hinton,et al. Semantic hashing , 2009, Int. J. Approx. Reason..

[10] Geoffrey E. Hinton. A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.