Interpreting Image Classifiers by Generating Discrete Masks
Deep models are commonly treated as black-boxes and lack interpretability. Here, we propose a novel approach to interpret deep image classifiers by generating discrete masks. Our method follows the generative adversarial network formalism. The deep model to be interpreted is the discriminator while...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 4 vom: 06. Apr., Seite 2019-2030
|
|---|
| 1. Verfasser: |
Yuan, Hao
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Cai, Lei,
Hu, Xia,
Wang, Jie,
Ji, Shuiwang |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|