Exemplar Free Counting On Fsc147
Métriques
MAE(test)
MAE(val)
RMSE(test)
RMSE(val)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | MAE(test) | MAE(val) | RMSE(test) | RMSE(val) | Paper Title | Repository |
|---|---|---|---|---|---|---|
| FamNet | 32.27 | 32.15 | 131.46 | 98.75 | Learning To Count Everything | |
| RCC | 17.12 | 17.49 | 104.53 | 58.81 | Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision | |
| LOCA | 16.2 | 17.43 | 103.96 | 54.96 | A Low-Shot Object Counting Network With Iterative Prototype Adaptation | |
| RepRPN-Counter | 26.66 | 29.24 | 129.11 | 98.11 | Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers | |
| SAVE | 8.92 | 8.89 | 80.39 | 35.83 | SAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting | |
| GCA-SUN | 14.00 | 16.06 | 92.19 | 53.04 | GCA-SUN: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting | - |
| CounTR | 14.71 | 18.07 | 106.87 | 71.84 | CounTR: Transformer-based Generalised Visual Counting | |
| DAVE | 15.14 | 15.54 | 103.49 | 52.67 | DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting | |
| GeCo | 13.30 | 14.81 | 108.72 | 64.95 | A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation |
0 of 9 row(s) selected.