Research map / Probabilistic and scientific modeling / Molecules and proteins
FBLNet: FeedBack Loop Network for Driver Attention Prediction
Yilong Chen, Zhixiong Nan, Tao Xiang
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 feedback loop to the incremental-knowledge guided fusion (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.7624 -> 1.8505 | Improved |
| use incremental-knowledge guided Transformer fusion instead of addition (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.7357 -> 1.7624 | Improved |
| use guided fusion instead of concatenation (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.6777 -> 1.7624 | Improved |
| take feedback from decoder layer d2 instead of d4 (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.7679 -> 1.8505 | Improved |
| take feedback from decoder layer d2 instead of d0 (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.7625 -> 1.8505 | Improved |
| combine CNN and Transformer encoders instead of CNN only (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.7538 -> 1.8505 | Improved |
| combine CNN and Transformer encoders instead of Transformer only (ablation) | FBLNet · DADA + BDDA | average of SIM, CC, NSS: 1.7265 -> 1.8505 | Improved |
| use FBLNet versus best baseline on BDDA | driver attention prediction · BDDA | CC: 0.5698 -> 0.6447 | Improved |
| use FBLNet versus best baseline on DADA SIM and Kldiv | driver attention prediction · DADA | SIM: 0.3728 -> 0.3307 | Mixed |
Closest papers by meaning
- DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance (CVPR 2026 · similarity 0.89)
- SalM²: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention (AAAI 2025 · similarity 0.88)
- DriveGazen: Event-Based Driving Status Recognition Using Conventional Camera (AAAI 2025 · similarity 0.85)
- FIFA: Fine-grained Inter-frame Attention for Driver's Video Gaze Estimation (CVPR 2025 · similarity 0.84)
- Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving (NeurIPS 2024 · similarity 0.84)
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.83)
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.
