Research map / Detection and segmentation / CNN features
Predictive Feature Learning for Future Segmentation Prediction
Zihang Lin, Jiangxin Sun, Jian-Fang Hu, Qizhi Yu, Jian-Huang Lai, Wei-Shi Zheng
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 multi-scale feature fusion in the autoencoder (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 short-term: 47.5 -> 48.7 | Improved |
| add multi-scale feature fusion in the autoencoder (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 mid-term: 28.8 -> 30.5 | Improved |
| add rescaling blocks in encoder and decoder (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 short-term: 45.7 -> 47.5 | Improved |
| add rescaling blocks in encoder and decoder (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 mid-term: 26.4 -> 28.8 | Improved |
| add the full autoencoder before prediction (ablation) | feature prediction model · Cityscapes future instance segmentation | AP50 short-term: 44.2 -> 48.7 | Improved |
| add the full autoencoder before prediction (ablation) | feature prediction model · Cityscapes future instance segmentation | AP50 mid-term: 24.7 -> 30.5 | Improved |
| add reconstruction loss in the bidirectional prediction module (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 short-term: 47.9 -> 48.7 | Improved |
| add reconstruction loss in the bidirectional prediction module (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 mid-term: 29.4 -> 30.5 | Improved |
| predict feature residual between neighboring frames instead of next-frame feature (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 short-term: 47.0 -> 48.7 | Improved |
| predict feature residual between neighboring frames instead of next-frame feature (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 mid-term: 28.5 -> 30.5 | Improved |
| use predictive feature resolution k=4 instead of k=2 (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 mid-term: 23.5 -> 30.5 | Improved |
| use predictive feature resolution k=4 instead of k=5 (ablation) | Predictive Feature Autoencoder · Cityscapes future instance segmentation | AP50 mid-term: 29.4 -> 30.5 | Improved |
Closest papers by meaning
- Predicting Future Instance Segmentation by Forecasting Convolutional Features (ECCV 2018 · similarity 0.86)
- Predicting Deeper Into the Future of Semantic Segmentation (ICCV 2017 · similarity 0.86)
- APANet: Auto-Path Aggregation for Future Instance Segmentation Prediction (TPAMI 2021 · similarity 0.83)
- Self-supervision through Random Segments with Autoregressive Coding (RandSAC) (ICLR 2023 · similarity 0.83)
- Seg-VAR:Image Segmentation with Visual Autoregressive Modeling (NeurIPS 2025 · similarity 0.82)
- VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning (ICLR 2025 · similarity 0.81)
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.
