OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
arXiv:2004.09033 · doi:10.1109/TIP.2020.2990277
Abstract
A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting in small-sample classification, learning more discriminative features from small-sample data is becoming a new trend. To this end, this paper aims to find a subspace of neural networks that can facilitate a large decision margin. Specifically, we propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain orthogonal during both the training and test processes. The Rademacher complexity of a network using the OSL is only , where is the number of classes, of that of a network using the fully connected classification layer, leading to a tighter generalization error bound. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets, as well as its applicability to large-sample datasets. Codes are available at: https://github.com/dongliangchang/OSLNet.
TIP 2020. Code available at https://github.com/dongliangchang/OSLNet
References in corpus (32)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Distilling the Knowledge in a Neural Network
- Improving neural networks by preventing co-adaptation of feature detectors
- Prototypical Networks for Few-shot Learning
- How transferable are features in deep neural networks?
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- Deep Visual Domain Adaptation: A Survey
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Temporal Ensembling for Semi-Supervised Learning
- Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
- Deep Convolutional Inverse Graphics Network
- Transductive Multi-view Zero-Shot Learning
- The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
- Generalizing to Unseen Domains via Adversarial Data Augmentation
- Data Programming: Creating Large Training Sets, Quickly
- One-shot Learning with Memory-Augmented Neural Networks
- Dropout Training as Adaptive Regularization
- Unitary Evolution Recurrent Neural Networks
- Few-Example Object Detection with Model Communication
- Learning to Compose Domain-Specific Transformations for Data Augmentation
- Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
- Swapout: Learning an ensemble of deep architectures
- Snapshot Ensembles: Train 1, get M for free
- Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
- Regularizing CNNs with Locally Constrained Decorrelations
- TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
- Hyperspherical Prototype Networks
- Deep Hyperspherical Learning
- Small Sample Learning in Big Data Era
- Decorrelated Batch Normalization
- Virtual Class Enhanced Discriminative Embedding Learning