On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study
arXiv:2104.02653 · doi:10.1016/j.eswa.2021.114991
Abstract
Deep learning models need large amounts of data for training. In video recognition and classification, significant advances were achieved with the introduction of new large databases. However, the creation of large-databases for training is infeasible in several scenarios. Thus, existing or small collected databases are typically joined and amplified to train these models. Nevertheless, training neural networks on limited data is not straightforward and comes with a set of problems. In this paper, we explore the effects of stacking databases, model initialization, and data amplification techniques when training with limited data on deep learning models' performance. We focused on the problem of Facial Expression Recognition from videos. We performed an extensive study with four databases at a different complexity and nine deep-learning architectures for video classification. We found that (i) complex training sets translate better to more stable test sets when trained with transfer learning and synthetically generated data, but their performance yields a high variance; (ii) training with more detailed data translates to more stable performance on novel scenarios (albeit with lower performance); (iii) merging heterogeneous data is not a straightforward improvement, as the type of augmentation and initialization is crucial; (iv) classical data augmentation cannot fill the holes created by joining largely separated datasets; and (v) inductive biases help to bridge the gap when paired with synthetic data, but this data is not enough when working with standard initialization techniques.
arXiv commentTo appear in Expert Systems with Applications
References in corpus (21)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
- The Effectiveness of Data Augmentation in Image Classification using Deep Learning
- GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
- Deep Facial Expression Recognition: A Survey
- Training Very Deep Networks
- Going Deeper in Facial Expression Recognition using Deep Neural Networks
- Training Generative Adversarial Networks with Limited Data
- Spatial-Temporal Recurrent Neural Network for Emotion Recognition
- GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
- Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
- Learning to Compose Domain-Specific Transformations for Data Augmentation
- A Survey on Face Data Augmentation
- Learning Character-Agnostic Motion for Motion Retargeting in 2D
- Recognition of facial expressions based on salient geometric features and support vector machines
- Implicit Semantic Data Augmentation for Deep Networks
- Video-based Facial Expression Recognition using Graph Convolutional Networks
- Self-Paced Video Data Augmentation with Dynamic Images Generated by Generative Adversarial Networks