Research map / Point clouds / Segmentation and detection
Learning Permutation Invariant Representations using Memory Networks
Shivam Kalra, Mohammed Adnan, Graham Taylor, H.R. Tizhoosh
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 |
|---|---|---|---|
| use MEM memory block with mean pooling instead of Deep Sets mean pooling | FF + Mean · Sum of Even Digits | MAE: 0.2958 -> 0.2437 | Improved |
| add MEM memory block before max pooling | FF + Max · Sum of Even Digits | MAE: 1.3292 -> 0.2295 | Improved |
| add MEM memory block before dot-product pooling | FF + Dotprod · Sum of Even Digits | MAE: 1.8015 -> 0.3932 | Improved |
| add MEM memory block before sum pooling | FF + Sum · Sum of Even Digits | MAE: 0.5763 -> 0.2739 | Improved |
| add MEM memory block before mean pooling | FF + Mean · Prime Sum | accuracy: 0.5280 -> 0.7208 | Improved |
| add MEM memory block before max pooling | FF + Max · Prime Sum | accuracy: 0.9257 -> 0.9361 | Improved |
| add MEM memory block before max pooling | FF + Max · Maximum of Set | accuracy: 0.9585 -> 0.9498 | Hurt |
| add MEM memory block before mean pooling | FF + Mean · Maximum of Set | accuracy: 0.3223 -> 0.9445 | Improved |
| add MEM memory block before dot-product pooling | FF + Dotprod · Gaussian Clustering | NLL: 8.538 -> 1.363 | Improved |
| add MEM memory block before sum pooling | FF + Sum · TCGA LUAD vs LUSC | accuracy: 0.5159 -> 0.8484 | Improved |
| add MEM memory block before mean pooling | FF + Mean · TCGA LUAD vs LUSC | accuracy: 0.7777 -> 0.8465 | Improved |
| add MEM memory block before dot-product pooling | FF + Dotprod · TCGA LUAD vs LUSC | accuracy: 0.4112 -> 0.6345 | Improved |
Closest papers by meaning
- Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification (CVPR 2024 · similarity 0.83)
- Memory-Efficient Prompt Tuning for Incremental Histopathology Classification (AAAI 2024 · similarity 0.83)
- Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning (CVPR 2025 · similarity 0.83)
- Rotation-Agnostic Image Representation Learning for Digital Pathology (CVPR 2024 · similarity 0.83)
- MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification (NeurIPS 2025 · similarity 0.83)
- Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis (CVPR 2024 · 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.
