# Deep Quantization: Encoding Convolutional Activations with Deep Generative Model

Source: [Deep Quantization: Encoding Convolutional Activations with Deep Generative Model](<https://www.sota2.com/research/paper/68fa63031e209131ce9fc548>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:31:19.733Z

Authors: Zhaofan Qiu, Ting Yao, Tao Mei

Published: 2016-11-29T06:07:28.000Z

## Abstract

Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher Vector encoding with Variational Auto-Encoder (FV-VAE), a novel deep architecture that quantizes the local activations of convolutional layer in a deep generative model, by training them in an end-to-end manner. To incorporate FV encoding strategy into deep generative models, we introduce Variational Auto-Encoder model, which steers a variational inference and learning in a neural network which can be straightforwardly optimized using standard stochastic gradient method. Different from the FV characterized by conventional generative models (e.g., Gaussian Mixture Model) which parsimoniously fit a discrete mixture model to data distribution, the proposed FV-VAE is more flexible to represent the natural property of data for better generalization. Extensive experiments are conducted on three public datasets, i.e., UCF101, ActivityNet, and CUB-200-2011 in the context of video action recognition and fine-grained image classification, respectively. Superior results are reported when compared to state-of-the-art representations. Most remarkably, our proposed FV-VAE achieves to-date the best published accuracy of 94.2% on UCF101.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1611.09502>)

[PDF](<https://arxiv.org/pdf/1611.09502.pdf>)
