AdaResNet: Enhancing Residual Networks with Dynamic Weight Adjustment for Improved Feature Integration
This addresses a specific bottleneck in training deep neural networks for researchers and practitioners, but it is incremental as it builds directly on ResNet.
The paper tackles the problem of equal treatment of input and transformed data in ResNet skip connections by proposing AdaResNet, which dynamically adjusts their ratio during training, resulting in up to a 50% accuracy improvement over traditional ResNet.
In very deep neural networks, gradients can become extremely small during backpropagation, making it challenging to train the early layers. ResNet (Residual Network) addresses this issue by enabling gradients to flow directly through the network via skip connections, facilitating the training of much deeper networks. However, in these skip connections, the input ipd is directly added to the transformed data tfd, treating ipd and tfd equally, without adapting to different scenarios. In this paper, we propose AdaResNet (Auto-Adapting Residual Network), which automatically adjusts the ratio between ipd and tfd based on the training data. We introduce a variable, weight}_{tfd}^{ipd, to represent this ratio. This variable is dynamically adjusted during backpropagation, allowing it to adapt to the training data rather than remaining fixed. Experimental results demonstrate that AdaResNet achieves a maximum accuracy improvement of over 50\% compared to traditional ResNet.