Training compact deep learning models for video classification using circulant matrices
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.
Code (1)
Tasks
General ClassificationVideo ClassificationSimilar Papers 제목 키워드 기반
Understanding and Training Deep Diagonal Circulant Neural Networks
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 ClassificationThe Expressive Power of Deep Neural Networks with Circulant Matrices
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 ClassificationEdgeLDR: Quaternion Low-Displacement Rank Neural Networks for Edge-Efficient Deep Learning
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 ClassificationMemory Capacity of Neural Networks using a Circulant Weight Matrix
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
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