mlsanityData to 14 Oct 2026

a novel attention-based network for fast salient object detection

arXiv 2112.10481 ↗First posted 20 Dec 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on the limited memory device. Some others shallow layer network will not maintain the same accuracy compared with U-shape structure and the deep network structure with more parameters will not converge to a global minimum loss with great speed. To overcome all of these disadvantages, we proposed a new deep convolution network architecture with three contributions: (1) using smaller convolution neural networks (CNNs) to compress the model in our improved salient object features compression and reinforcement extraction module (ISFCREM) to reduce parameters of the model. (2) introducing channel attention mechanism in ISFCREM to weigh different channels for improving the ability of feature representation. (3) applying a new optimizer to accumulate the long-term gradient information during training to adaptively tune the learning rate. The results demonstrate that the proposed method can compress the model to 1/3 of the original size nearly without losing the accuracy and converging faster and more smoothly on six widely used datasets of salient object detection compared with the others models. Our code is published in https://gitee.com/binzhangbinzhangbin/code-a-novel-attention-based-network-for-fast-salient-object-detection.git

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 47 references that are in the map. First posted on arXiv 20 Dec 2021.

Builds on

23 of 47 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  8. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  9. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  10. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  11. 2019Cascaded Partial Decoder for Fast and Accurate Salient Object Detectioncited by 216
  12. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 212
11 more
  1. 2014The Secrets of Salient Object Segmentationcited by 200
  2. 2016Deeply supervised salient object detection with short connectionscited by 196
  3. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  4. 2018Reverse Attention for Salient Object Detectioncited by 113
  5. 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89
  6. 2016Deep Contrast Learning for Salient Object Detectioncited by 52
  7. 2017Learning Uncertain Convolutional Features for Accurate Saliency Detectioncited by 44
  8. 2017Instance-Level Salient Object Segmentationcited by 38
  9. 2015Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Networkcited by 31
  10. 2016Deep Saliency with Encoded Low level Distance Map and High Level Featurescited by 23
  11. 2020AdaX: Adaptive Gradient Descent with Exponential Long Term Memorycited by 10

Built on by

Not cited yet.