Research map / Detection and segmentation / CNN features
SuperVAE: Superpixelwise Variational Autoencoder for Salient Object Detection
Bo Li, Zhengxing Sun, Yuqi Guo
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 perceptual loss from VGG19 hidden layers (ablation) | SuperVAE · ECSSD | max F-measure: 0.759 -> 0.828 | Improved |
| add perceptual loss (ablation) | SuperVAE · ECSSD | MAE: 0.138 -> 0.103 | Improved |
| add background sample selection via boundary connectivity (ablation) | SuperVAE · ECSSD | max F-measure: 0.813 -> 0.828 | Improved |
| add background sample selection (ablation) | SuperVAE · ASD | max F-measure: 0.862 -> 0.867 | Improved |
| add multi-scale fusion (ablation) | SuperVAE · ECSSD | max F-measure: 0.821 -> 0.828 | Improved |
| add multi-scale fusion (ablation) | SuperVAE · SOD | MAE: 0.164 -> 0.159 | Improved |
| unsupervised SuperVAE vs best unsupervised baseline MST | SuperVAE · ECSSD | max F-measure: 0.705 -> 0.828 | Improved |
| unsupervised training instead of pixel-level supervised (vs LRF) | SuperVAE · ECSSD | max F-measure: 0.880 -> 0.828 | Hurt |
Closest papers by meaning
- Non-Local Deep Features for Salient Object Detection (CVPR 2017 · similarity 0.89)
- Deep Level Sets for Salient Object Detection (CVPR 2017 · similarity 0.89)
- BASNet: Boundary-Aware Salient Object Detection (CVPR 2019 · similarity 0.88)
- Detection of Co-salient Objects by Looking Deep and Wide (IJCV 2016 · similarity 0.87)
- Towards High-Resolution Salient Object Detection (ICCV 2019 · similarity 0.87)
- Salient Object Detection with Recurrent Fully Convolutional Networks (TPAMI 2018 · 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.
