I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911128424022016 |
|---|---|
| author | Karine, Ayoub Napoléon, Thibault Jridi, Maher |
| author_facet | Karine, Ayoub Napoléon, Thibault Jridi, Maher |
| contents | This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring knowledge between the intermediate layers of teacher (cumbersome model) and student (compact model). For knowledge extraction, we exploit class prototypes derived from feature maps. To facilitate knowledge transfer, we employ a triplet loss in order to minimize intra-class variances and maximize inter-class variances between teacher and student prototypes. Consequently, I2CKD enables the student to better mimic the feature representation of the teacher for each class, thereby enhancing the segmentation performance of the compact network. Extensive experiments on three segmentation datasets, i.e., Cityscapes, Pascal VOC and CamVid, using various teacher-student network pairs demonstrate the effectiveness of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18490 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation Karine, Ayoub Napoléon, Thibault Jridi, Maher Computer Vision and Pattern Recognition This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring knowledge between the intermediate layers of teacher (cumbersome model) and student (compact model). For knowledge extraction, we exploit class prototypes derived from feature maps. To facilitate knowledge transfer, we employ a triplet loss in order to minimize intra-class variances and maximize inter-class variances between teacher and student prototypes. Consequently, I2CKD enables the student to better mimic the feature representation of the teacher for each class, thereby enhancing the segmentation performance of the compact network. Extensive experiments on three segmentation datasets, i.e., Cityscapes, Pascal VOC and CamVid, using various teacher-student network pairs demonstrate the effectiveness of the proposed method. |
| title | I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.18490 |