Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

• URL: http://arxiv.org/abs/2402.00422v1
• Date: Thu, 1 Feb 2024 08:39:31 GMT
• Title: Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
• Authors: Zhuo Su, Jiehua Zhang, Longguang Wang, Hua Zhang, Zhen Liu, Matti Pietik\"ainen, Li Liu
• Abstract summary: We propose two novel types of convolutions, dubbed emphPixel Difference Convolution (PDC) and Binary PDC (Bi-PDC) We present two lightweight deep networks named emphPixel Difference Networks (PiDiNet) and emph Binary PiDiNet (Bi-PiDiNet) respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition.
• Score: 20.345417462198725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient DNNs lies in how to balance the competing goals of achieving high accuracy and high efficiency. In this paper we propose two novel types of convolutions, dubbed \emph{Pixel Difference Convolution (PDC) and Binary PDC (Bi-PDC)} which enjoy the following benefits: capturing higher-order local differential information, computationally efficient, and able to be integrated with existing DNNs. With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition. Extensive experiments on popular datasets (BSDS500, ImageNet, LFW, YTF, \emph{etc.}) show that PiDiNet and Bi-PiDiNet achieve the best accuracy-efficiency trade-off. For edge detection, PiDiNet is the first network that can be trained without ImageNet, and can achieve the human-level performance on BSDS500 at 100 FPS and with $<$1M parameters. For object recognition, among existing Binary DNNs, Bi-PiDiNet achieves the best accuracy and a nearly $2\times$ reduction of computational cost on ResNet18. Code available at \href{https://github.com/hellozhuo/pidinet}{https://github.com/hellozhuo/pidinet}.

Related papers

• MogaNet: Multi-order Gated Aggregation Network [64.16774341908365]
  We propose a new family of modern ConvNets, dubbed MogaNet, for discriminative visual representation learning. MogaNet encapsulates conceptually simple yet effective convolutions and gated aggregation into a compact module. MogaNet exhibits great scalability, impressive efficiency of parameters, and competitive performance compared to state-of-the-art ViTs and ConvNets on ImageNet.
  arXiv  Detail & Related papers  (2022-11-07T04:31:17Z)
• DA$^{\textbf{2}}$-Net : Diverse & Adaptive Attention Convolutional Neural Network [0.6999740786886536]
  DA$2$-Net enables feed-forward CNNs to explicitly capture diverse features and adaptively select and emphasize the most informative features to efficiently boost the network's performance. We extensively evaluated DA$2$-Net on benchmark datasets, including CIFAR100, SVHN, and ImageNet.
  arXiv  Detail & Related papers  (2021-11-25T16:25:16Z)
• Pixel Difference Networks for Efficient Edge Detection [71.03915957914532]
  We propose a lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue datasets are provided to demonstrate its effectiveness. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS.
  arXiv  Detail & Related papers  (2021-08-16T10:42:59Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search [13.467017642143583]
  We propose a novel of Network Candidate Search (NCS) to study the trade-off between the resource usage and the performance. In our experiment, we collect candidate CNN models from EfficientNet-B0 to be scaled down in varied way through width, depth, input resolution and compound scaling down. For further embracing the CNN edge application with Application-Specific Integrated Circuit (ASIC), we adjust the architectures of EfficientNet-eLite to build the more hardware-friendly version, EfficientNet-HF.
  arXiv  Detail & Related papers  (2020-09-16T01:11:10Z)
• Towards Lossless Binary Convolutional Neural Networks Using Piecewise Approximation [4.023728681102073]
  CNNs can significantly reduce the number of arithmetic operations and the size of memory storage. However, the accuracy degradation of single and multiple binary CNNs is unacceptable for modern architectures. We propose a Piecewise Approximation scheme for multiple binary CNNs which lessens accuracy loss by approximating full precision weights and activations.
  arXiv  Detail & Related papers  (2020-08-08T13:32:33Z)
• $\Pi-$nets: Deep Polynomial Neural Networks [86.36557534288535]
  $Pi$-Nets are neural networks in which the output is a high-order of the input. We empirically demonstrate that $Pi$-Nets have better representation power than standard DCNNs. Our framework elucidates why recent generative models, such as StyleGAN, improve upon their predecessors.
  arXiv  Detail & Related papers  (2020-03-08T18:48:43Z)
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions [76.05981545084738]
  We propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts. We show that the proposed ReActNet outperforms all the state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2020-03-07T02:12:02Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)
• MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy? [12.050205584630922]
  Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. In this paper, we present an architectural approach: MeliusNet. It consists of alternating a DenseBlock, which increases the feature capacity, and our proposed ImprovementBlock, which increases the feature quality.
  arXiv  Detail & Related papers  (2020-01-16T16:56:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.