paper-with-me

홈 › Papers

Mixture separability loss in a deep convolutional network for image classification

2019-06-16 · Trung Dung Do, Cheng-Bin Jin, Hakil Kim, Van Huan Nguyen

In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the network. However, using only cross-entropy loss causes a network to stop updating weights when all training images are correctly classified. This is the problem of the early saturation. This paper proposes a novel cost function, called mixture separability loss (MSL), which updates the weights of the network even when most of the training images are accurately predicted. MSL consists of between-class and within-class loss. Between-class loss maximizes the differences between inter-class images, whereas within-class loss minimizes the similarities between intra-class images. We designed the proposed loss function to attach to different convolutional layers in the network in order to utilize intermediate feature maps. Experiments show that a network with MSL deepens the learning process and obtains promising results with some public datasets, such as Street View House Number (SVHN), Canadian Institute for Advanced Research (CIFAR), and our self-collected Inha Computer Vision Lab (ICVL) gender dataset.

📄 PDF Abstract BibTeX arXiv:1906.06633

Code (0)

등록된 구현이 없습니다.

Tasks

General Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Learning to Navigate in the Gaussian Mixture Surface

2021-10-21 · CAIP: Computer Analysis of Images and Patterns 2021 10 · Riccardo La Grassa, Ignazio Gallo, Nicola Landro

In the last years, deep learning models have achieved remarkable generalization capability on computer vision tasks, obtaining excellent results in fine-grained classification problems. Sophisticated approaches based-on …

Navigate

MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings

2020-07-18 · Ali Varamesh, Tinne Tuytelaars

We present MIX'EM, a novel solution for unsupervised image classification. MIX'EM generates representations that by themselves are sufficient to drive a general-purpose clustering algorithm to deliver high-quality classi…

ClassificationClusteringGeneral Classificationimage-classification+3

Contrastive-center loss for deep neural networks

2017-07-24 · Ce Qi, Fei Su

The deep convolutional neural network(CNN) has significantly raised the performance of image classification and face recognition. Softmax is usually used as supervision, but it only penalizes the classification loss. In …

ClassificationFace RecognitionGeneral Classificationimage-classification+1

Boosting Network Weight Separability via Feed-Backward Reconstruction

2019-10-20 · Jongmin Yu, Hyeontaek Oh

This paper proposes a new evaluation metric and boosting method for weight separability in neural network design. In contrast to general visual recognition methods designed to encourage both intra-class compactness and i…

Face Recognitionimage-classificationImage Classification

Separation and Concentration in Deep Networks

2020-12-18 · John Zarka, Florentin Guth, Stéphane Mallat

Numerical experiments demonstrate that deep neural network classifiers progressively separate class distributions around their mean, achieving linear separability on the training set, and increasing the Fisher discrimina…

General Classificationimage-classificationImage Classification