Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2407.06339 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914862657961984 |
|---|---|
| author | Zhu, Hongbo Wulff, Theodor Maharjan, Rahul Singh Han, Jinpei Cangelosi, Angelo |
| author_facet | Zhu, Hongbo Wulff, Theodor Maharjan, Rahul Singh Han, Jinpei Cangelosi, Angelo |
| contents | Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have different emphases but are rather one-sided. They primarily analyse the attention mechanisms or gradient-based attribution while neglecting the magnitudes of input feature values or the skip-connection module. Moreover, they inevitably bring spurious noisy pixel attributions unrelated to the model's decision, hindering humans' trust in the spotted visualization result. Hence, we propose an easy-to-implement but effective way to remedy this flaw: Smooth Noise Norm Attention (SNNA). We weigh the attention by the norm of the transformed value vector and guide the label-specific signal with the attention gradient, then randomly sample the input perturbations and average the corresponding gradients to produce noise-free attribution. Instead of evaluating the explanation method on the binary or multi-class classification tasks like in previous works, we explore the more complex multi-label classification scenario in this work, i.e., the driving action prediction task, and trained a model for it specifically. Both qualitative and quantitative evaluation results show the superiority of SNNA compared to other SOTA attention-based explainable methods in generating a clearer visual explanation map and ranking the input pixel importance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06339 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Noise-Free Explanation for Driving Action Prediction Zhu, Hongbo Wulff, Theodor Maharjan, Rahul Singh Han, Jinpei Cangelosi, Angelo Computer Vision and Pattern Recognition Artificial Intelligence Although attention mechanisms have achieved considerable progress in Transformer-based architectures across various Artificial Intelligence (AI) domains, their inner workings remain to be explored. Existing explainable methods have different emphases but are rather one-sided. They primarily analyse the attention mechanisms or gradient-based attribution while neglecting the magnitudes of input feature values or the skip-connection module. Moreover, they inevitably bring spurious noisy pixel attributions unrelated to the model's decision, hindering humans' trust in the spotted visualization result. Hence, we propose an easy-to-implement but effective way to remedy this flaw: Smooth Noise Norm Attention (SNNA). We weigh the attention by the norm of the transformed value vector and guide the label-specific signal with the attention gradient, then randomly sample the input perturbations and average the corresponding gradients to produce noise-free attribution. Instead of evaluating the explanation method on the binary or multi-class classification tasks like in previous works, we explore the more complex multi-label classification scenario in this work, i.e., the driving action prediction task, and trained a model for it specifically. Both qualitative and quantitative evaluation results show the superiority of SNNA compared to other SOTA attention-based explainable methods in generating a clearer visual explanation map and ranking the input pixel importance. |
| title | Noise-Free Explanation for Driving Action Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.06339 |