paper-with-me

홈 › Papers

Factors of Transferability for a Generic ConvNet Representation

2014-06-22 · Hossein Azizpour, Ali Sharif Razavian, Josephine Sullivan, Atsuto Maki, Stefan Carlsson

Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, by optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their distance from the source task such that a correlation between the performance of tasks and their distance from the source task w.r.t. the proposed factors is observed.

📄 PDF Abstract BibTeX arXiv:1406.5774

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality ReductionRepresentation Learning

Similar Papers 제목 키워드 기반

Transferability of Spectral Graph Convolutional Neural Networks

2019-07-30 · Ron Levie, Wei Huang, Lorenzo Bucci, Michael M. Bronstein 외

This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset co…

Analyzing Filters Toward Efficient ConvNet

2018-06-01 · CVPR 2018 6 · Takumi Kobayashi

Deep convolutional neural network (ConvNet) is a promising approach for high-performance image classification. The behavior of ConvNet is analyzed mainly based on the neuron activations, such as by visualizing them. In t…

ClassificationGeneral Classificationimage-classificationImage Classification

Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification

2022-10-14 · Ricardo Montalvo-Lezama, Berenice Montalvo-Lezama, Gibran Fuentes-Pineda

In this paper, we study the transferability of ImageNet spatial and Kinetics spatio-temporal representations to multi-label Movie Trailer Genre Classification (MTGC). In particular, we present an extensive evaluation of …

Action RecognitionClassificationGenre classificationTemporal Action Localization+1

Personalizing Human Video Pose Estimation

2015-11-20 · CVPR 2016 6 · James Charles, Tomas Pfister, Derek Magee, David Hogg 외

We propose a personalized ConvNet pose estimator that automatically adapts itself to the uniqueness of a person's appearance to improve pose estimation in long videos. We make the following contributions: (i) we show tha…

Optical Flow EstimationPose Estimation

Visual Instance Retrieval with Deep Convolutional Networks

2014-12-20 · Ali Sharif Razavian, Josephine Sullivan, Stefan Carlsson, Atsuto Maki

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we pre…

Image RetrievalRetrieval