Compression of Deep Neural Networks for Image Instance Retrieval
Image instance retrieval is the problem of retrieving images from a database which contain the same object. Convolutional Neural Network (CNN) based descriptors are becoming the dominant approach for generating global image descriptors for the instance retrieval problem. One major drawback of CNN-ba...
Main Authors: | Chandrasekhar, Vijay, Lin, Jie, Morere, Olivier, Veillard, Antoine, Duan, Lingyu, Liao, Qianli, Poggio, Tomaso A |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
Format: | Article |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2017
|
Online Access: | http://hdl.handle.net/1721.1/112277 https://orcid.org/0000-0003-0076-621X https://orcid.org/0000-0002-3944-0455 |
Similar Items
-
Group Invariant Deep Representations for Image Instance Retrieval
by: Morère, Olivier, et al.
Published: (2016) -
Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval
by: Morère, Olivier, et al.
Published: (2017) -
Object-Oriented Deep Learning
by: Liao, Qianli, et al.
Published: (2017) -
Implicit dynamic regularization in deep networks
by: Poggio, Tomaso, et al.
Published: (2020) -
Theory II: Landscape of the Empirical Risk in Deep Learning
by: Poggio, Tomaso, et al.
Published: (2017)