Data Dropout: Optimizing Training Data for Convolutional Neural Networks

Abstract

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to particular tasks, hand-crafted information such as image prior has also been incorporated into end-to-end learning. However, very little progress has been made on investigating how an individual training sample will influence the generalization ability of a model. In other words, to achieve high generalization accuracy, do we really need all the samples in a training dataset? In this paper, we demonstrate that deep learning models such as convolutional neural networks may not favor all training samples, and generalization accuracy can be further improved by dropping those unfavorable samples. Specifically, the influence of removing a training sample is quantifiable, and we propose a Two-Round Training approach, aiming to achieve higher generalization accuracy. We locate unfavorable samples after the first round of training, and then retrain the model from scratch with the reduced training dataset in the second round. Since our approach is essentially different from fine-tuning or further training, the computational cost should not be a concern. Our extensive experimental results indicate that, with identical settings, the proposed approach can boost performance of the well-known networks on both high-level computer vision problems such as image classification, and low-level vision problems such as image denoising.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Striving for Simplicity: The All Convolutional Net
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Understanding Black-box Predictions via Influence Functions
• Deep Networks with Stochastic Depth

Cited by in corpus (5)

• Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications
• ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation
• Rethinking Influence Functions of Neural Networks in the Over-parameterized Regime
• Influence Function based Data Poisoning Attacks to Top-N Recommender Systems
• Instance-based Deep Transfer Learning