SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling

• URL: http://arxiv.org/abs/2207.11511v1
• Date: Sat, 23 Jul 2022 13:01:55 GMT
• Title: SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling
• Authors: Ho Man Kwan and Shenghui Song
• Abstract summary: We show that using adaptive sampling in the building blocks of a deep neural network can improve its efficiency. In particular, we propose SSBNet which is built by inserting sampling layers repeatedly into existing networks like ResNet. Experiment results show that the proposed SSBNet can achieve competitive image classification and object detection performance on ImageNet and datasets.
• Score: 1.7767466724342065
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another dimension reduction method, adaptive sampling weights and processes regions that are relevant to the task, and is thus able to better preserve useful information. However, the use of adaptive sampling has been limited to certain layers. In this paper, we show that using adaptive sampling in the building blocks of a deep neural network can improve its efficiency. In particular, we propose SSBNet which is built by inserting sampling layers repeatedly into existing networks like ResNet. Experiment results show that the proposed SSBNet can achieve competitive image classification and object detection performance on ImageNet and COCO datasets. For example, the SSB-ResNet-RS-200 achieved 82.6% accuracy on ImageNet dataset, which is 0.6% higher than the baseline ResNet-RS-152 with a similar complexity. Visualization shows the advantage of SSBNet in allowing different layers to focus on different positions, and ablation studies further validate the advantage of adaptive sampling over uniform methods.

Related papers

• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• Content-aware Scalable Deep Compressed Sensing [8.865549833627794]
  We present a novel content-aware scalable network dubbed CASNet to address image compressed sensing problems. We first adopt a data-driven saliency detector to evaluate the importances of different image regions and propose a saliency-based block ratio aggregation (BRA) strategy for sampling rate allocation. To accelerate training convergence and improve network robustness, we propose an SVD-based scheme and a random transformation enhancement (RTE) strategy.
  arXiv  Detail & Related papers  (2022-07-19T14:59:14Z)
• SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks [8.195696498474579]
  We propose a feedback-recursive convolutional framework (SalFBNet) for saliency detection. We create a large-scale Pseudo-Saliency dataset to alleviate the problem of data deficiency in saliency detection.
  arXiv  Detail & Related papers  (2021-12-07T14:39:45Z)
• supervised adptive threshold network for instance segmentation [4.347876036795798]
  Mask R-CNN method based on adaptive threshold. layered adaptive network structure. adaptive feature pool. Experiments on benchmark data sets indicate that the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2021-06-07T09:25:44Z)
• BCNet: Searching for Network Width with Bilaterally Coupled Network [56.14248440683152]
  We introduce a new supernet called Bilaterally Coupled Network (BCNet) to address this issue. In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately. Our method achieves state-of-the-art or competing performance over other baseline methods.
  arXiv  Detail & Related papers  (2021-05-21T18:54:03Z)
• Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions [5.725228891050467]
  We propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs) Inspired by the diverse effects on training from different samples, Selective Output Smoothing Regularization improves the performance by encouraging the model to produce equal logits on incorrect classes. This plug-and-play regularization method can be conveniently incorporated into almost any CNN-based project without extra hassle.
  arXiv  Detail & Related papers  (2021-03-29T07:21:06Z)
• MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling [86.42733428762513]
  MOPS-Net is a novel interpretable deep learning-based method for matrix optimization. We show that MOPS-Net can achieve favorable performance against state-of-the-art deep learning-based methods over various tasks.
  arXiv  Detail & Related papers  (2020-05-01T14:01:53Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)
• Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
  This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs. Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-06T15:51:00Z)
• Resolution Adaptive Networks for Efficient Inference [53.04907454606711]
  We propose a novel Resolution Adaptive Network (RANet), which is inspired by the intuition that low-resolution representations are sufficient for classifying "easy" inputs. In RANet, the input images are first routed to a lightweight sub-network that efficiently extracts low-resolution representations. High-resolution paths in the network maintain the capability to recognize the "hard" samples.
  arXiv  Detail & Related papers  (2020-03-16T16:54:36Z)

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.