Adaptive Pixel-wise Structured Sparse Network for Efficient CNNs

• URL: http://arxiv.org/abs/2010.11083v3
• Date: Sat, 20 Mar 2021 08:46:42 GMT
• Title: Adaptive Pixel-wise Structured Sparse Network for Efficient CNNs
• Authors: Chen Tang, Wenyu Sun, Zhuqing Yuan, Yongpan Liu
• Abstract summary: This paper proposes a novel spatially adaptive framework that can generate pixel-wise sparsity according to the input image. A sparse controlling method is presented to enable online adjustment for applications with different precision/latency requirements.
• Score: 11.377052459168942
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image. The sparse scheme is pixel-wise refined, regional adaptive under a unified importance map, which makes it friendly to hardware implementation. A sparse controlling method is further presented to enable online adjustment for applications with different precision/latency requirements. The sparse model is applicable to a wide range of vision tasks. Experimental results show that this method efficiently improve the computing efficiency for both image classification using ResNet-18 and super resolution using SRResNet. On image classification task, our method can save 30%-70% MACs with a slightly drop in top-1 and top-5 accuracy. On super resolution task, our method can reduce more than 90% MACs while only causing around 0.1 dB and 0.01 decreasing in PSNR and SSIM. Hardware validation is also included.

Related papers

• Efficient Context Integration through Factorized Pyramidal Learning for Ultra-Lightweight Semantic Segmentation [1.0499611180329804]
  We propose a novel Factorized Pyramidal Learning (FPL) module to aggregate rich contextual information in an efficient manner. We decompose the spatial pyramid into two stages which enables a simple and efficient feature fusion within the module to solve the notorious checkerboard effect. Based on the FPL module and FIR unit, we propose an ultra-lightweight real-time network, called FPLNet, which achieves state-of-the-art accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-02-23T05:34:51Z)
• Efficient fine-grained road segmentation using superpixel-based CNN and CRF models [0.0]
  We propose a novel approach to utilise the advantages of CNNs for the task of road segmentation at reasonable computational effort. The proposed system obtained comparable performance among the top performing algorithms on the KITTI road benchmark.
  arXiv  Detail & Related papers  (2022-06-22T12:38:30Z)
• EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications [68.35683849098105]
  We introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K. Our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-06-21T17:59:56Z)
• Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution [64.54162195322246]
  Convolutional neural network (CNN) has achieved great success on image super-resolution (SR) Most deep CNN-based SR models take massive computations to obtain high performance. We propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
  arXiv  Detail & Related papers  (2022-03-16T20:10:41Z)
• New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis [0.1503974529275767]
  This paper proposes a robust feature extraction method for SAR image target classification by adaptively fusing effective features from different CNN layers. Experiments on the MSTAR dataset demonstrate that the proposed method outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-10-28T18:10:26Z)
• Greedy Network Enlarging [53.319011626986004]
  We propose a greedy network enlarging method based on the reallocation of computations. With step-by-step modifying the computations on different stages, the enlarged network will be equipped with optimal allocation and utilization of MACs. With application of our method on GhostNet, we achieve state-of-the-art 80.9% and 84.3% ImageNet top-1 accuracies.
  arXiv  Detail & Related papers  (2021-07-31T08:36:30Z)
• Enhancing sensor resolution improves CNN accuracy given the same number of parameters or FLOPS [53.10151901863263]
  We show that it is almost always possible to modify a network such that it achieves higher accuracy at a higher input resolution while having the same number of parameters or/and FLOPS. Preliminary empirical investigation over MNIST, Fashion MNIST, and CIFAR10 datasets demonstrates the efficiency of the proposed approach.
  arXiv  Detail & Related papers  (2021-03-09T06:47:01Z)
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification [46.885260723836865]
  Deep convolutional neural networks (CNNs) generally improve when fueled with high resolution images. Inspired by the fact that not all regions in an image are task-relevant, we propose a novel framework that performs efficient image classification. Our framework is general and flexible as it is compatible with most of the state-of-the-art light-weighted CNNs.
  arXiv  Detail & Related papers  (2020-10-11T17:55:06Z)
• Learning to Learn Parameterized Classification Networks for Scalable Input Images [76.44375136492827]
  Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. We employ meta learners to generate convolutional weights of main networks for various input scales. We further utilize knowledge distillation on the fly over model predictions based on different input resolutions.
  arXiv  Detail & Related papers  (2020-07-13T04:27:25Z)

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.