Beyond softmax loss: Intra-concentration and inter-separability loss for classification
نویسندگان
چکیده
منابع مشابه
Semantic Softmax Loss for Zero-Shot Learning
A typical pipeline for Zero-Shot Learning (ZSL) is to integrate the visual features and the class semantic descriptors into a multimodal framework with a linear or bilinear model. However, the visual features and the class semantic descriptors locate in different structural spaces, a linear or bilinear model can not capture the semantic interactions between different modalities well. In this le...
متن کاملLarge-Margin Softmax Loss for Convolutional Neural Networks
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 does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages int...
متن کاملL2-constrained Softmax Loss for Discriminative Face Verification
In recent years, the performance of face verification systems has significantly improved using deep convolutional neural networks (DCNNs). A typical pipeline for face verification includes training a deep network for subject classification with softmax loss, using the penultimate layer output as the feature descriptor, and generating a cosine similarity score given a pair of face images. The so...
متن کاملClassification and Comparison of Methods for Discovering Coverage Loss Areas in Wireless Sensor Networks
In recent years, wireless sensor networks data is taken into consideration as an ideal source, in terms of speed, accuracy and cost, in order to study the Earth's surface. One of the most important challenges in this area, is the signaling network coverage and finding holes. In recent years, wireless sensor networks data is taken into consideration as an ideal source, in terms of speed, accurac...
متن کاملHierarchical loss for classification
Failing to distinguish between a sheepdog and a skyscraper should be worse and penalized more than failing to distinguish between a sheepdog and a poodle; after all, sheepdogs and poodles are both breeds of dogs. However, existing metrics of failure (so-called “loss” or “win”) used in textual or visual classification/recognition via neural networks seldom view a sheepdog as more similar to a po...
متن کاملذخیره 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
DOI: 10.1016/j.neucom.2020.11.030