Attention Incorporate Network: A network can adapt various data size
Liangbo He, Hao Sun

TL;DR
The paper introduces Attention Incorporate Network (AIN), a novel neural network architecture that effectively handles inputs of various sizes across different data types by leveraging an attention mechanism, improving accuracy and convergence.
Contribution
AIN is the first network that adapts to various input sizes across multiple data types using attention, avoiding information loss from deformation.
Findings
AIN achieves higher accuracy than traditional models.
AIN demonstrates better convergence during training.
AIN effectively processes images, text, and audio of different sizes.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Visual Attention and Saliency Detection · Neural Networks and Applications
MethodsSigmoid Activation · Tanh Activation · Long Short-Term Memory
