Research map / Detection and segmentation / CNN features
End-to-End Robust Joint Unsupervised Image Alignment and Clustering
Xiangrui Zeng, Gregory Howe, Min Xu
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 the alignment branch jointly trained with clustering (ablation) | Jim-Net clustering · Simulated cryo-ET, SNR 0.05 | clustering accuracy: 62.8 -> 96.1 | Improved |
| add the alignment branch jointly trained with clustering (ablation) | Jim-Net clustering · Simulated cryo-ET, SNR 0.03 | clustering accuracy: 51.3 -> 85.5 | Improved |
| add the alignment branch jointly trained with clustering (ablation) | Jim-Net clustering · Simulated cryo-ET, SNR 0.01 | clustering accuracy: 35.3 -> 48.1 | Improved |
| add the alignment branch jointly trained with clustering (ablation) | Jim-Net clustering · Simulated cryo-ET, SNR 100 | clustering accuracy: 99.5 -> 100 | Improved |
| add the alignment branch jointly trained with clustering (ablation) | Jim-Net clustering · Air-water interface single-particle | overall clustering accuracy: 85.4 -> 96.6 | Improved |
| joint learning with clustering instead of alignment only (Gum-Net) | Jim-Net alignment · Simulated cryo-ET, SNR 0.1 | rotation error: 0.62 -> 0.51 | Improved |
| joint learning with clustering instead of alignment only (Gum-Net) | Jim-Net alignment · Simulated cryo-ET, SNR 0.01 | rotation error: 1.50 -> 1.58 | Hurt |
| joint learning with clustering instead of alignment only (Gum-Net) | Jim-Net alignment · Simulated cryo-ET, SNR 100 | translation error: 1.59 -> 1.28 | Improved |
Closest papers by meaning
- SCCS: Deep Neural Spectral Clustering for Self-Supervised Subcellular Structure Segmentation (AAAI 2025 · similarity 0.84)
- FastJAM: a Fast Joint Alignment Model for Images (NeurIPS 2025 · similarity 0.84)
- Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo-Labeling (AAAI 2025 · similarity 0.83)
- BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment (CVPR 2025 · similarity 0.83)
- $\epsilon$-Seg: Sparsely Supervised Semantic Segmentation of Microscopy Data (NeurIPS 2025 · similarity 0.83)
- Alleviate and Mining: Rethinking Unsupervised Domain Adaptation for Mitochondria Segmentation from Pseudo-Label Perspective (AAAI 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.
