Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery

Haonan Lin, Wenbin An, Jiahao Wang, Yan Chen, Feng Tian, Mengmeng Wang, QianYing Wang, Guang Dai, Jingdong Wang

Keywords: generalized category discovery, semi-supervised learning, open world learning

TL;DR: FlipClass introduces a dynamic teacher-student framework for GCD, aligning the teacher's attention with the student's feedback to ensure consistent pattern learning and synchronized classification across old and new classes.

Abstract: 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 generalized category discovery as compared to their success in closed-world semi-supervised learning. We identify inconsistent pattern learning 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-attention-update strategy refines the teacher's focus based on student feedback, 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.

Primary Area: Machine vision

Submission Number: 466