Research map / Detection and segmentation / CNN features
Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection
Chunshui Cao, Yongzhen Huang, Zilei Wang, Liang Wang, Ninglong Xu, Tieniu Tan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add lateral inhibition to top-down gradients (vs LI off) (ablation) | LICNN saliency · HKU-IS | maxF: 0.510 -> 0.841 | Improved |
| add lateral inhibition to top-down gradients (vs LI off) (ablation) | LICNN saliency · DUT-OMRON | maxF: 0.360 -> 0.677 | Improved |
| use lateral inhibition model instead of average denoising plus mean thresholding (ablation) | LICNN saliency · HKU-IS | maxF: 0.759 -> 0.841 | Improved |
| add saliency map optimization of Zhu et al. 2014 (ablation) | LICNN saliency · HKU-IS | maxF: 0.798 -> 0.841 | Improved |
| add saliency map optimization of Zhu et al. 2014 (ablation) | LICNN saliency · DUT-OMRON | MAE: 0.154 -> 0.138 | Improved |
| use LICNN instead of c-MWP for category-specific attention | VGG16 · VOC07 Pointing Game difficult | mean accuracy (%): 66.8 -> 70.0 | Improved |
| use LICNN instead of c-MWP with GoogleNet | GoogleNet · VOC07 Pointing Game all | mean accuracy (%): 85.0 -> 87.9 | Improved |
| weak-supervised LICNN vs strongly supervised MDF | saliency detection · DUT-OMRON | maxF: 0.694 -> 0.677 | Mixed |
Closest papers by meaning
- Progressive Attention Guided Recurrent Network for Salient Object Detection (CVPR 2018 · similarity 0.86)
- Learn to Pay Attention (ICLR 2018 · similarity 0.86)
- Multi-Source Weak Supervision for Saliency Detection (CVPR 2019 · similarity 0.85)
- Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (ICCV 2019 · similarity 0.85)
- Shallow and Deep Convolutional Networks for Saliency Prediction (CVPR 2016 · similarity 0.85)
- Predicting When Saliency Maps Are Accurate and Eye Fixations Consistent (CVPR 2016 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
