Related papers: Stitching for Neuroevolution: Recombining Deep Neu…
We propose StitchNet, a novel neural network creation paradigm that stitches together fragments (one or more consecutive network layers) from multiple pre-trained neural networks. StitchNet allows the creation of high-performing neural…
Model stitching (Lenc & Vedaldi 2015) is a compelling methodology to compare different neural network representations, because it allows us to measure to what degree they may be interchanged. We expand on a previous work from Bansal,…
Deep learning has been shown to be very capable at performing many real-world tasks. However, this performance is often dependent on the presence of large and varied datasets. In some settings, like in the medical domain, data is often…
Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network's size is needed, it is necessary to retrain from scratch, which is expensive. To avoid…
Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting. However, in practice the network architecture…
We revisit and extend model stitching (Lenc & Vedaldi 2015) as a methodology to study the internal representations of neural networks. Given two trained and frozen models $A$ and $B$, we consider a "stitched model'' formed by connecting the…
The public model zoo containing enormous powerful pretrained model families (e.g., ResNet/DeiT) has reached an unprecedented scope than ever, which significantly contributes to the success of deep learning. As each model family consists of…
We propose a simple scheme for merging two neural networks trained with different starting initialization into a single one with the same size as the original ones. We do this by carefully selecting channels from each input network. Our…
Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels…
Taking inspiration from biological evolution, we explore the idea of "Can deep neural networks evolve naturally over successive generations into highly efficient deep neural networks?" by introducing the notion of synthesizing new highly…
We employ a toolset -- dubbed Dr. Frankenstein -- to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a…
Network pruning is widely used to lighten and accelerate neural network models. Structured network pruning discards the whole neuron or filter, leading to accuracy loss. In this work, we propose a novel concept of neuron merging applicable…
A deep residual network, built by stacking a sequence of residual blocks, is easy to train, because identity mappings skip residual branches and thus improve information flow. To further reduce the training difficulty, we present a simple…
Multi-task learning in Convolutional Networks has displayed remarkable success in the field of recognition. This success can be largely attributed to learning shared representations from multiple supervisory tasks. However, existing…
Spiking neural networks (SNNs) have closer dynamics to the brain than current deep neural networks. Their low power consumption and sample efficiency make these networks interesting. Recently, several deep convolutional spiking neural…
With the rapid development of deep learning, a growing number of pre-trained models have been publicly available. However, deploying these fixed models in real-world IoT applications is challenging because different devices possess…
One of the most promising ways of improving the performance of deep convolutional neural networks is by increasing the number of convolutional layers. However, adding layers makes training more difficult and computationally expensive. In…
Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-based image stitching solutions are rarely studied due to the…
We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…
In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary…