Research map / Detection and segmentation / CNN features
Deep Learning for Light Field Saliency Detection
Tiantian Wang, Yongri Piao, Xiao Li, Lihe Zhang, Huchuan 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 focal stack stream to all-focus image (ablation) | two-stream VGG19 network (late fusion + att + LSTM) · LFSD | maxF: 0.817 -> 0.863 | Improved |
| add focal stack stream to all-focus image (ablation) | two-stream VGG19 network (late fusion + att + LSTM) · Our light field dataset | maxF: 0.819 -> 0.868 | Improved |
| early integration of focal slices instead of all-focus only (ablation) | VGG19 stream · Our light field dataset | maxF: 0.819 -> 0.847 | Improved |
| layer-wise integration instead of all-focus only (ablation) | VGG19 stream · Our light field dataset | maxF: 0.819 -> 0.823 | No clear effect |
| late integration by element-wise addition instead of all-focus only (ablation) | VGG19 stream · Our light field dataset | maxF: 0.819 -> 0.822 | No clear effect |
| add attention without ConvLSTM to late fusion (ablation) | late fusion (d) · Our light field dataset | MAE: 0.110 -> 0.227 | Hurt |
| add ConvLSTM on top of attention (ablation) | late fusion + att · Our light field dataset | maxF: 0.819 -> 0.863 | Improved |
| add ConvLSTM on top of attention (ablation) | late fusion + att · LFSD | MAE: 0.236 -> 0.100 | Improved |
| add adversarial examples to fine-tuning (ablation) | att + LSTM model · LFSD | maxF: 0.851 -> 0.863 | Improved |
| add adversarial examples to fine-tuning (ablation) | att + LSTM model · Our light field dataset | MAE: 0.072 -> 0.070 | Improved |
| add adversarial examples to fine-tuning (ablation) | att + LSTM model · Our light field dataset | maxF: 0.863 -> 0.868 | Improved |
Closest papers by meaning
- A Thorough Benchmark and a New Model for Light Field Saliency Detection (TPAMI 2023 · similarity 0.92)
- Memory-oriented Decoder for Light Field Salient Object Detection (NeurIPS 2019 · similarity 0.92)
- Exploit and Replace: An Asymmetrical Two-Stream Architecture for Versatile Light Field Saliency Detection (AAAI 2020 · similarity 0.91)
- Learning From Pixel-Level Noisy Label: A New Perspective for Light Field Saliency Detection (CVPR 2022 · similarity 0.91)
- Light Field Saliency Detection With Dual Local Graph Learning and Reciprocative Guidance (ICCV 2021 · similarity 0.90)
- Saliency Detection on Light Field (TPAMI 2016 · similarity 0.89)
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.
