Research map / Detection and segmentation / CNN features
Look, Perceive and Segment: Finding the Salient Objects in Images via Two-Stream Fixation-Semantic CNNs
Xiaowu Chen, Anlin Zheng, Jia Li, Feng Lu
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 the fixation stream (ablation) | FSN · DUT-OMRON | Fmax_beta: 0.753 -> 0.768 | Improved |
| add the fixation stream (ablation) | FSN · DUT-OMRON | MAE: 0.080 -> 0.065 | Improved |
| use pre-trained fixation stream output instead of zeros (ablation) | FSN · DUT-OMRON | Fmax_beta: .723 -> 0.768 | Improved |
| pre-train fixation stream on eye-tracking data instead of random init (ablation) | FSN · DUT-OMRON | Fmax_beta: .759 -> 0.768 | No clear effect |
| add the inception-like block (ablation) | FSN · DUT-OMRON | Fmax_beta: 0.752 -> 0.768 | Improved |
| add the inception-like block (ablation) | FSN · DUT-OMRON | MAE: .068 -> 0.065 | Improved |
| add the Butterworth layer (ablation) | FSN · DUT-OMRON | Fmax_beta: .773 -> 0.768 | No clear effect |
| add the Butterworth layer (ablation) | FSN · DUT-OMRON | MAE: .101 -> 0.065 | Improved |
| apply Butterworth filter to LEGS | LEGS · HKU-IS | MAE: 0.129 | Improved |
| apply Butterworth filter to MDF | FSN · HKU-IS | MAE: 0.087 | Improved |
Closest papers by meaning
- Saliency Unified: A Deep Architecture for Simultaneous Eye Fixation Prediction and Salient Object Segmentation (CVPR 2016 · similarity 0.92)
- Salient Object Detection Driven by Fixation Prediction (CVPR 2018 · similarity 0.90)
- Inferring Salient Objects from Human Fixations (TPAMI 2019 · similarity 0.90)
- Salient Object Detection with Recurrent Fully Convolutional Networks (TPAMI 2018 · similarity 0.88)
- A Stagewise Refinement Model for Detecting Salient Objects in Images (ICCV 2017 · similarity 0.87)
- An Integrated Model for Effective Saliency Prediction (AAAI 2017 · similarity 0.87)
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.
