Related papers: TResNet: High Performance GPU-Dedicated Architectu…
Since the breakthrough performance of AlexNet in 2012, convolutional neural networks (convnets) have grown into extremely powerful vision models. Deep learning researchers have used convnets to perform vision tasks with accuracy that was…
Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here we consider the problem of inference, the application of a…
Deep neural networks have made significant progress in the field of computer vision. Recent studies have shown that depth, width and shortcut connections of neural network architectures play a crucial role in their performance. One of the…
Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance, like the remarkable work ConvNeXt which employs 7x7…
Deep learning network training is usually computationally expensive and intuitively complex. We present a novel network architecture for custom training and weight evaluations. We reformulate the layers as ResNet-similar blocks with certain…
State-of-the-art deep learning models for computer vision tasks are based on the transformer architecture and often deployed in real-time applications. In this scenario, the resources available for every inference can vary, so it is useful…
Much recent research has been dedicated to improving the efficiency of training and inference for image classification. This effort has commonly focused on explicitly improving theoretical efficiency, often measured as ImageNet validation…
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…
Residual neural networks are widely used in computer vision tasks. They enable the construction of deeper and more accurate models by mitigating the vanishing gradient problem. Their main innovation is the residual block which allows the…
Major winning Convolutional Neural Networks (CNNs), such as VGGNet, ResNet, DenseNet, \etc, include tens to hundreds of millions of parameters, which impose considerable computation and memory overheads. This limits their practical usage in…
Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains…
In this paper, we present MicroNet, which is an efficient convolutional neural network using extremely low computational cost (e.g. 6 MFLOPs on ImageNet classification). Such a low cost network is highly desired on edge devices, yet usually…
Edge detection has made significant progress with the help of deep Convolutional Networks (ConvNet). These ConvNet based edge detectors have approached human level performance on standard benchmarks. We provide a systematical study of these…
Past few years have witnessed exponential growth of interest in deep learning methodologies with rapidly improving accuracies and reduced computational complexity. In particular, architectures using Convolutional Neural Networks (CNNs) have…
The application of TensorFlow pre-trained models in deep learning is explored, with an emphasis on practical guidance for tasks such as image classification and object detection. The study covers modern architectures, including ResNet,…
We develop an approach to growing deep network architectures over the course of training, driven by a principled combination of accuracy and sparsity objectives. Unlike existing pruning or architecture search techniques that operate on…
This paper presents a novel approach to network pruning, targeting block pruning in deep neural networks for edge computing environments. Our method diverges from traditional techniques that utilize proxy metrics, instead employing a direct…
CNNs have been shown to maintain reasonable classification accuracy when quantized to lower precisions. Quantizing to sub 8-bit activations and weights can result in accuracy falling below an acceptable threshold. Techniques exist for…
This paper aims at addressing the problem of substantial performance degradation at extremely low computational cost (e.g. 5M FLOPs on ImageNet classification). We found that two factors, sparse connectivity and dynamic activation function,…
Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still…