Weakly Supervised Object Localization On 2
评估指标
GT-known localization accuracy
Top-1 Localization Accuracy
average top-1 classification accuracy
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||||
|---|---|---|---|---|---|
| Stable diffusion | 75.0 | 65.2 | - | Generative Prompt Model for Weakly Supervised Object Localization | |
| Deit-S | 68.8 | 56.1 | 76.7 | Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration | |
| CexCNN | 67.65 | - | - | Causal Explanation of Convolutional Neural Networks | - |
| TokenCut | 65.4 | 52.3 | - | Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut | |
| FALcon | 62.45 | 49.39 | - | Exploring Foveation and Saccade for Improved Weakly-Supervised Localization | - |
| R-Mix (ResNet-50) | - | 55.58 | - | Expeditious Saliency-guided Mix-up through Random Gradient Thresholding |
0 of 6 row(s) selected.