Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910666361667584 |
|---|---|
| author | Lin, Haonan An, Wenbin Wang, Jiahao Chen, Yan Tian, Feng Wang, Mengmeng Dai, Guang Wang, Qianying Wang, Jingdong |
| author_facet | Lin, Haonan An, Wenbin Wang, Jiahao Chen, Yan Tian, Feng Wang, Mengmeng Dai, Guang Wang, Qianying Wang, Jingdong |
| contents | Recent advancements have shown promise in applying traditional Semi-Supervised Learning strategies to the task of Generalized Category Discovery (GCD). Typically, this involves a teacher-student framework in which the teacher imparts knowledge to the student to classify categories, even in the absence of explicit labels. Nevertheless, GCD presents unique challenges, particularly the absence of priors for new classes, which can lead to the teacher's misguidance and unsynchronized learning with the student, culminating in suboptimal outcomes. In our work, we delve into why traditional teacher-student designs falter in open-world generalized category discovery as compared to their success in closed-world semi-supervised learning. We identify inconsistent pattern learning across attention layers as the crux of this issue and introduce FlipClass, a method that dynamically updates the teacher to align with the student's attention, instead of maintaining a static teacher reference. Our teacher-student attention alignment strategy refines the teacher's focus based on student feedback from an energy perspective, promoting consistent pattern recognition and synchronized learning across old and new classes. Extensive experiments on a spectrum of benchmarks affirm that FlipClass significantly surpasses contemporary GCD methods, establishing new standards for the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19659 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery Lin, Haonan An, Wenbin Wang, Jiahao Chen, Yan Tian, Feng Wang, Mengmeng Dai, Guang Wang, Qianying Wang, Jingdong Computer Vision and Pattern Recognition Recent advancements have shown promise in applying traditional Semi-Supervised Learning strategies to the task of Generalized Category Discovery (GCD). Typically, this involves a teacher-student framework in which the teacher imparts knowledge to the student to classify categories, even in the absence of explicit labels. Nevertheless, GCD presents unique challenges, particularly the absence of priors for new classes, which can lead to the teacher's misguidance and unsynchronized learning with the student, culminating in suboptimal outcomes. In our work, we delve into why traditional teacher-student designs falter in open-world generalized category discovery as compared to their success in closed-world semi-supervised learning. We identify inconsistent pattern learning across attention layers as the crux of this issue and introduce FlipClass, a method that dynamically updates the teacher to align with the student's attention, instead of maintaining a static teacher reference. Our teacher-student attention alignment strategy refines the teacher's focus based on student feedback from an energy perspective, promoting consistent pattern recognition and synchronized learning across old and new classes. Extensive experiments on a spectrum of benchmarks affirm that FlipClass significantly surpasses contemporary GCD methods, establishing new standards for the field. |
| title | Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.19659 |