Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914762773757952 |
|---|---|
| author | Nguyen, Quoc Khanh Nguyen, Truong Thanh Hung Nguyen, Vo Thanh Khang Truong, Van Binh Phan, Tuong Cao, Hung |
| author_facet | Nguyen, Quoc Khanh Nguyen, Truong Thanh Hung Nguyen, Vo Thanh Khang Truong, Van Binh Phan, Tuong Cao, Hung |
| contents | To address the challenges of providing quick and plausible explanations in Explainable AI (XAI) for object detection models, we introduce the Gaussian Class Activation Mapping Explainer (G-CAME). Our method efficiently generates concise saliency maps by utilizing activation maps from selected layers and applying a Gaussian kernel to emphasize critical image regions for the predicted object. Compared with other Region-based approaches, G-CAME significantly reduces explanation time to 0.5 seconds without compromising the quality. Our evaluation of G-CAME, using Faster-RCNN and YOLOX on the MS-COCO 2017 dataset, demonstrates its ability to offer highly plausible and faithful explanations, especially in reducing the bias on tiny object detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13417 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer Nguyen, Quoc Khanh Nguyen, Truong Thanh Hung Nguyen, Vo Thanh Khang Truong, Van Binh Phan, Tuong Cao, Hung Computer Vision and Pattern Recognition Artificial Intelligence To address the challenges of providing quick and plausible explanations in Explainable AI (XAI) for object detection models, we introduce the Gaussian Class Activation Mapping Explainer (G-CAME). Our method efficiently generates concise saliency maps by utilizing activation maps from selected layers and applying a Gaussian kernel to emphasize critical image regions for the predicted object. Compared with other Region-based approaches, G-CAME significantly reduces explanation time to 0.5 seconds without compromising the quality. Our evaluation of G-CAME, using Faster-RCNN and YOLOX on the MS-COCO 2017 dataset, demonstrates its ability to offer highly plausible and faithful explanations, especially in reducing the bias on tiny object detection. |
| title | Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.13417 |