paper-with-me

홈 › Papers

Learning Discriminative Features Via Weights-biased Softmax Loss

2019-04-25 · XiaoBin Li, Weiqiang Wang

Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or maximization of inter-class variance. In the early studies, there is no theoretical analysis and experiments explicitly indicating how to choose the number of units in fully connected layer. To help CNNs learn features more fast and discriminative, there are two contributions in this paper. First, we determine the minimum number of units in FC layer by rigorous theoretical analysis and extensive experiment, which reduces CNNs' parameter memory and training time. Second, we propose a negative-focused weights-biased softmax (W-Softmax) loss to help CNNs learn more discriminative features. The proposed W-Softmax loss not only theoretically formulates the intraclass compactness and inter-class separability, but also can avoid overfitting by enlarging decision margins. Moreover, the size of decision margins can be flexibly controlled by adjusting a hyperparameter $\alpha$. Extensive experimental results on several benchmark datasets show the superiority of W-Softmax in image classification tasks.

📄 PDF Abstract BibTeX arXiv:1904.11138

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

X2-Softmax: Margin Adaptive Loss Function for Face Recognition

2023-12-08 · Jiamu Xu, Xiaoxiang Liu, Xinyuan Zhang, Yain-Whar Si 외

Learning the discriminative features of different faces is an important task in face recognition. By extracting face features in neural networks, it becomes easy to measure the similarity of different face images, which …

Face Recognition

Large-Margin Softmax Loss for Convolutional Neural Networks

2016-12-07 · Weiyang Liu, Yandong Wen, Zhiding Yu, Meng Yang

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component…

General Classification

Support Vector Guided Softmax Loss for Face Recognition

2018-12-29 · Xiaobo Wang, Shuo Wang, Shifeng Zhang, Tianyu Fu 외

Face recognition has witnessed significant progresses due to the advances of deep convolutional neural networks (CNNs), the central challenge of which, is feature discrimination. To address it, one group tries to exploit…

Face Recognition

Facial Expression Recognition in the Wild via Deep Attentive Center Loss

2021-01-07 · Amir Hossein Farzaneh, Xiaojun Qi

Learning discriminative features for Facial Expression Recognition (FER) in the wild using Convolutional Neural Networks (CNNs) is a non-trivial task due to the significant intra-class variations and inter-class similari…

Facial Expression RecognitionFacial Expression Recognition (FER)Feature ImportanceMetric Learning

Imbalance Robust Softmax for Deep Embeeding Learning

2020-11-23 · Hao Zhu, Yang Yuan, Guosheng Hu, Xiang Wu 외

Deep embedding learning is expected to learn a metric space in which features have smaller maximal intra-class distance than minimal inter-class distance. In recent years, one research focus is to solve the open-set prob…

Face RecognitionPerson Re-Identification