paper-with-me

Papers

Training compact deep learning models for video classification using circulant matrices

2018-10-02 · Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif

In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which makes them difficult to train and to deploy, especially on mobile devices. In this paper, we build on recent results at the crossroads of Linear Algebra and Deep Learning which demonstrate how imposing a structure on large weight matrices can be used to reduce the size of the model. We propose very compact models for video classification based on state-of-the-art network architectures such as Deep Bag-of-Frames, NetVLAD and NetFisherVectors. We then conduct thorough experiments using the large YouTube-8M video classification dataset. As we will show, the circulant DBoF embedding achieves an excellent trade-off between size and accuracy.

📄 PDF Abstract BibTeX arXiv:1810.01140

Code (1)

araujoalexandre/youtube8m-circulant 공식 구현 tf

Tasks

General ClassificationVideo Classification

Similar Papers 제목 키워드 기반

Understanding and Training Deep Diagonal Circulant Neural Networks

2019-01-29 · Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif

In this paper, we study deep diagonal circulant neural networks, that is deep neural networks in which weight matrices are the product of diagonal and circulant ones. Besides making a theoretical analysis of their expres…

Video Classification

The Expressive Power of Deep Neural Networks with Circulant Matrices

2019-05-01 · ICLR 2019 5 · Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif

Recent results from linear algebra stating that any matrix can be decomposed into products of diagonal and circulant matrices has lead to the design of compact deep neural network architectures that perform well in pract…

General ClassificationVideo Classification

EdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learning

2026-01-08 · Vladimir Frants, Sos Agaian, Karen Panetta arxiv

Deploying deep neural networks on edge devices is often limited by the memory traffic and compute cost of dense linear operators. While quaternion neural networks improve parameter efficiency by coupling multiple channel…

Hyperspectral Image Classification

Memory Capacity of Neural Networks using a Circulant Weight Matrix

2014-03-12 · Vamsi Sashank Kotagiri

This paper presents results on the memory capacity of a generalized feedback neural network using a circulant matrix. Children are capable of learning soon after birth which indicates that the neural networks of the brai…

Event Retrieval in Large Video Collections with Circulant Temporal Encoding

2013-06-01 · CVPR 2013 6 · Jerome Revaud, Matthijs Douze, Cordelia Schmid, Herve Jegou

This paper presents an approach for large-scale event retrieval. Given a video clip of a specific event, e.g., the wedding of Prince William and Kate Middleton, the goal is to retrieve other videos representing the same …

Copy DetectionQuantizationRetrieval