Research map / Label-efficient and robust learning / Recognition and long-tail
Spherical Procrustes Alignment for Reliable Medical Audio Diagnosis
Ying Wang, Guoheng Huang, Chan-Tong Lam, Xiaochen Yuan
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 spherical branch (L2 normalization) (ablation) | BEATs · ICBHI 2017 4-class (BEATs) | ECE (%): 28.51 -> 19.37 | Improved |
| add fixed ETF geometry (ablation) | BEATs + Spherical branch · ICBHI 2017 4-class (BEATs) | ECE (%) / AS: ECE 19.37 -> 9.37; AS 63.96 -> 62.83 | Mixed |
| add dynamic Procrustes alignment (ablation) | BEATs + Spherical + ETF · ICBHI 2017 4-class (BEATs) | ECE (%) / AS: ECE 9.37 -> 4.87; AS 62.83 -> 63.48 | Improved |
| add self-distillation (KL between branches) (ablation) | BEATs + Spherical + ETF + Procrustes · ICBHI 2017 4-class (BEATs) | ECE (%) / AS: AS 63.48 -> 64.42; ECE 4.87 -> 4.44 | Improved |
| add SPA | BEATs · ICBHI 2017 4-class (BEATs) | ECE (%): 28.51 -> 4.44 | Improved |
| add SPA | PAFA · ICBHI 2017 4-class | Average Score (%): 64.45 -> 65.27 | Improved |
| add SPA | M2D · CirCor DigiScope | ECE (%): 9.17 -> 4.63 | Improved |
| use Focal Loss or LDAM-DRW instead of CE | CNN6 · ICBHI 2017 4-class | Average Score (%): 58.66 -> 57.14 (Focal), 56.93 (LDAM-DRW) | Hurt |
| use Mixup | BEATs · ICBHI 2017 4-class (BEATs) | Average Score (%): 63.90 -> 62.16 | Hurt |
| use Label Smoothing | BEATs · ICBHI 2017 4-class (BEATs) | ECE (%): 28.51 -> 33.91 | Hurt |
| use Temperature Scaling | BEATs · ICBHI 2017 4-class (BEATs) | ECE (%): 28.51 -> 21.99 | Improved |
| use MC Dropout or Deep Ensembles (5 passes) | BEATs · ICBHI 2017 4-class (BEATs) | inference time (ms): 4.1 -> 19.1 (MC Dropout), 20.5 (Deep Ensembles) | Hurt |
Closest papers by meaning
- Weighted Manifold Alignment using Wave Kernel Signatures for Aligning Medical Image Datasets (TPAMI 2019 · similarity 0.82)
- Leveraging Anatomical Consistency for Multi-Object Detection in Ultrasound Images via Source-free Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.81)
- MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding (AAAI 2025 · similarity 0.80)
- U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding (ICLR 2026 · similarity 0.80)
- On the Fourier analysis in the SO(3) space : the EquiLoPO Network (ICLR 2025 · similarity 0.79)
- Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis (ICLR 2026 · similarity 0.79)
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.
