no code implementations • 18 Jan 2017 • Vijay Chandrasekhar, Jie Lin, Qianli Liao, Olivier Morère, Antoine Veillard, Ling-Yu Duan, Tomaso Poggio
One major drawback of CNN-based {\it global descriptors} is that uncompressed deep neural network models require hundreds of megabytes of storage making them inconvenient to deploy in mobile applications or in custom hardware.
no code implementations • 15 Mar 2016 • Olivier Morère, Jie Lin, Antoine Veillard, Vijay Chandrasekhar, Tomaso Poggio
The first one is Nested Invariance Pooling (NIP), a method inspired from i-theory, a mathematical theory for computing group invariant transformations with feed-forward neural networks.
no code implementations • 9 Jan 2016 • Olivier Morère, Antoine Veillard, Jie Lin, Julie Petta, Vijay Chandrasekhar, Tomaso Poggio
Based on a thorough empirical evaluation using several publicly available datasets, we show that our method is able to significantly and consistently improve retrieval results every time a new type of invariance is incorporated.
no code implementations • 10 Nov 2015 • Jie Lin, Olivier Morère, Julie Petta, Vijay Chandrasekhar, Antoine Veillard
Then, triplet networks, a rank learning scheme based on weight sharing nets is used to fine-tune the binary embedding functions to retain as much as possible of the useful metric properties of the original space.
no code implementations • 11 Aug 2015 • Vijay Chandrasekhar, Jie Lin, Olivier Morère, Hanlin Goh, Antoine Veillard
The second part of the study focuses on the impact of geometrical transformations such as rotations and scale changes.
no code implementations • 30 Jan 2015 • Olivier Morère, Hanlin Goh, Antoine Veillard, Vijay Chandrasekhar, Jie Lin
A comprehensive user study is conducted comparing our proposed method to a variety of schemes, including the summarization currently in use by one of the most popular video sharing websites.
no code implementations • 20 Jan 2015 • Jie Lin, Olivier Morere, Vijay Chandrasekhar, Antoine Veillard, Hanlin Goh
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval.