Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN).
Image source: Learning Deep Features for Discriminative Localization
Source: Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 62 | 15.01% |
Weakly-Supervised Semantic Segmentation | 50 | 12.11% |
Object Localization | 26 | 6.30% |
Weakly-Supervised Object Localization | 19 | 4.60% |
Image Classification | 18 | 4.36% |
Classification | 14 | 3.39% |
General Classification | 11 | 2.66% |
Weakly supervised segmentation | 9 | 2.18% |
Pseudo Label | 8 | 1.94% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |