Sequential Image Classification
31 papers with code • 3 benchmarks • 2 datasets
Sequential image classification is the task of classifying a sequence of images.
( Image credit: TensorFlow-101 )
Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory.
Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly.
We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed.
A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies.
When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes difficult due to the well studied issue of vanishing and exploding gradients, especially when trying to learn long-term dependencies.