Research map / Label-efficient and robust learning / Self-supervised and contrastive
DySeT: a Dynamic Masked Self-distillation Approach for Robust Trajectory Prediction
Mozghan Pourkeshavarz, Arielle Zhang, Amir Rasouli
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 |
|---|---|---|---|
| replace random masking with dynamic informativeness-based token sampling (ablation) | masked trajectory autoencoder · Argoverse2 val | minFDE6: 1.486 -> 1.306 | Improved |
| add masked self-distillation from EMA teacher (ablation) | DySeT · Argoverse2 val | minADE6: 0.751 -> 0.724 | Improved |
| set distillation weight lambda too high (10) (ablation) | DySeT · Argoverse2 val | minADE6: 0.724 -> 0.804 | Hurt |
| use dynamic sampling at high masking ratio (70%) versus random sampling (ablation) | DySeT · Argoverse2 val | minADE6: minADE 0.724, minFDE 1.278 | Improved |
| DySeT versus Forecast-MAE in unseen cities (finetune) | DySeT · Argoverse2 val unseen cities | minFDE6: 1.613 -> 1.328 | Improved |
| DySeT versus Forecast-MAE under targeted adversarial perturbation | DySeT · Argoverse2 val | PRS (%): 78.51 -> 86.83 | Improved |
| DySeT versus GP-Graph and GroupNet on UNIV source domain | DySeT · ETH/UCY unseen domains, UNIV | minADE20: 0.61 vs GP-Graph 0.54 | Hurt |
| DySeT versus Forecast-MAE finetune on single-modal metric | DySeT · Argoverse2 test | minFDE1: 4.35 -> 4.41 | Hurt |
Closest papers by meaning
- CaDeT: a Causal Disentanglement Approach for Robust Trajectory Prediction in Autonomous Driving (CVPR 2024 · similarity 0.87)
- LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations (NeurIPS 2024 · similarity 0.87)
- T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory (CVPR 2024 · similarity 0.86)
- Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting (CVPR 2025 · similarity 0.86)
- On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving (CVPR 2024 · similarity 0.86)
- Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling (NeurIPS 2025 · similarity 0.86)
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.
