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

TL;DR

This paper introduces FlipClass, a novel teacher-student framework for generalized category discovery that dynamically aligns teacher attention with the student's focus, improving learning consistency and performance in open-world scenarios.

Contribution

FlipClass innovatively updates the teacher based on student feedback, addressing the limitations of static teachers in open-world GCD and enhancing pattern learning across classes.

Findings

FlipClass outperforms existing GCD methods on multiple benchmarks.

Dynamic teacher updating improves pattern consistency across classes.

Attention alignment leads to better recognition of new and old categories.

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 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.