Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery
This work addresses the challenge of open-world category discovery without prior knowledge, offering a novel solution for applications like image classification, though it is incremental in improving teacher-student frameworks.
The paper tackled the problem of teacher-student misalignment in Generalized Category Discovery (GCD), where traditional methods fail due to inconsistent pattern learning, and introduced FlipClass to dynamically align teacher attention with student feedback, achieving significant performance improvements over existing GCD methods.
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.