Research map / Vision-language and multimodal / Cross-modal learning
Missing Modalities Imputation via Cascaded Residual Autoencoder
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use cascaded residual autoencoders with joint optimization rather than the strongest reported baseline | CRA · GRSS | PSNR: 30.05 -> 31.04 | Helped |
| Use cascaded residual autoencoders with joint optimization rather than the strongest reported baseline | CRA · RGB-D | NMSE: 0.331 -> 0.248 | Helped |
| Use cascaded residual autoencoders with joint optimization rather than the strongest reported baseline | CRA · MTPIE | recognition rate (%): 54.24 -> 56.42 | Helped |
| Use convolutional residual autoencoders rather than the strongest reported baseline | CRA · HSFD | PSNR: 26.33 -> 28.01 | Helped |
| Add joint optimization of the stacked residual autoencoders (ablation) | CRA · GRSS | PSNR: 30.80 -> 31.04 | Helped |
| Add joint optimization of the stacked residual autoencoders (ablation) | CRA · RGB-D | PSNR: 25.25 -> 25.93 | Helped |
| Add convolutional residual autoencoders (ablation) | CRA · HSFD | PSNR: 27.51 -> 28.01 | Helped |
| Increase the cascade depth from 1 to 5 residual autoencoders (ablation) | CRA · HSFD | PSNR: 26.27 -> 28.01 | Helped |
| Increase the cascade depth from 1 to 5 residual autoencoders (ablation) | CRA · HSFD | NMSE: 0.233 -> 0.209 | Helped |
| Increase the cascade depth from 1 to 5 residual autoencoders (ablation) | CRA · HSFD | recognition rate (%): 76.42 -> 78.03 | Helped |
| Use layer-by-layer training rather than end-to-end training (ablation) | CRA · All four datasets | imputation error | Helped |
| Use aggressive rather than one-shot CRA training (ablation) | CRA · GRSS | number of residual autoencoders: 3.4 RAs vs 5.6 RAs | Helped |
Closest papers by meaning
- Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo (NeurIPS 2022 · similarity 0.85)
- LDS2AE: Local Diffusion Shared-Specific Autoencoder for Multimodal Remote Sensing Image Classification with Arbitrary Missing Modalities (AAAI 2024 · similarity 0.84)
- Multi-Modal Object Re-identification via Sparse Mixture-of-Experts (ICML 2025 · similarity 0.83)
- MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification (NeurIPS 2025 · similarity 0.82)
- RedCore: Relative Advantage Aware Cross-Modal Representation Learning for Missing Modalities with Imbalanced Missing Rates (AAAI 2024 · similarity 0.82)
- RobSense: A Robust Multi-modal Foundation Model for Remote Sensing with Static, Temporal, and Incomplete Data Adaptability (CVPR 2025 · similarity 0.82)
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.