Attention Incorporate Network: A network can adapt various data size
This addresses a limitation in traditional neural networks that require fixed input sizes, offering a solution for flexible data processing across multiple domains, though it appears incremental as it builds on existing attention mechanisms.
The paper tackles the problem of training neural networks with varying input sizes across images, text, and audio by proposing the Attention Incorporate Network (AIN), which uses attention mechanisms to extract key features without relying on data size, achieving higher accuracy and better convergence compared to same-size networks.
In traditional neural networks for image processing, the inputs of the neural networks should be the same size such as 224*224*3. But how can we train the neural net model with different input size? A common way to do is image deformation which accompany a problem of information loss (e.g. image crop or wrap). Sequence model(RNN, LSTM, etc.) can accept different size of input like text and audio. But one disadvantage for sequence model is that the previous information will become more fragmentary during the transfer in time step, it will make the network hard to train especially for long sequential data. In this paper we propose a new network structure called Attention Incorporate Network(AIN). It solve the problem of different size of inputs including: images, text, audio, and extract the key features of the inputs by attention mechanism, pay different attention depends on the importance of the features not rely on the data size. Experimentally, AIN achieve a higher accuracy, better convergence comparing to the same size of other network structure