Competing ratio loss for discriminative multi-class image classification

نویسندگان

چکیده

The development of deep convolutional neural network architecture is critical to the improvement image classification task performance. Many studies use and focus on modifying structure improve Conversely, our study focuses loss function design. Cross-entropy Loss (CEL) has been widely used for training multi-class classification. Although CEL successfully implemented in several tasks, it only posterior probability correct class. For this reason, a negative log likelihood ratio (NLLR) was proposed better differentiate between class competing incorrect ones. However, during network, value NLLR not always positive or negative, which severely affects convergence NLLR. Our (CRL) calculates classes further enlarge difference classes. We added hyperparameters CRL, thereby ensuring its be that update size backpropagation suitable CRL’s fast convergence. To demonstrate performance we conducted experiments general tasks (CIFAR10/100, SVHN, ImageNet), fine-grained (CUB200–2011, Stanford Car), challenging face age estimation (using Adience). Experimental results showed effectiveness robustness different architectures tasks. Code released at https://github.com/guoyurong0104/CRL-code.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Discriminative Tensor Sparse Coding for Image Classification

A novel approach to learn a discriminative dictionary over a tensor sparse model is presented. A structural incoherence constraint between dictionary atoms from different classes is introduced to promote discriminating information into the dictionary. The incoherence term encourages dictionary atoms to be as independent as possible. In addition, we incorporate classification error into the obje...

متن کامل

Learning discriminative spatial representation for image classification

Spatial Pyramid Representation (SPR) [7] introduces spatial layout information to the orderless bag-of-features (BoF) representation. SPR has become the standard and has been shown to perform competitively against more complex methods for incorporating spatial layout. In SPR the image is divided into regular grids. However, the grids are taken as uniform spatial partitions without any theoretic...

متن کامل

Discriminative models for robust image classification

A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available training data are insufficient to learn accurate models, is a significant challenge. This dissertation explores the development of discriminative models for...

متن کامل

Discriminative Methods for Multi-labeled Classification

In this paper we present methods of enhancing existing discriminative classifiers for multi-labeled predictions. Discriminative methods like support vector machines perform very well for uni-labeled text classification tasks. Multi-labeled classification is a harder task subject to relatively less attention. In the multi-labeled setting, classes are often related to each other or part of a is-a...

متن کامل

Multi-class SVMs for Image Classification using Feature Tracking

The authors would like to thank O. Chapelle and B. Schölkopf for useful discussions and M. Giese and F. Wichmann for helpful comments about the manuscript. The authors were supported by a grant from the EC (COGVIS). Abstract. In this paper a novel representation for image classification is proposed which exploits the temporal information inherent in natural visual input. Image sequences are rep...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Neurocomputing

سال: 2021

ISSN: ['0925-2312', '1872-8286']

DOI: https://doi.org/10.1016/j.neucom.2021.08.106