Frequency-Aware Token Reduction for Efficient Vision Transformer
This work addresses efficiency challenges in Vision Transformers for computer vision applications, representing an incremental improvement over existing token reduction methods by incorporating frequency characteristics.
The paper tackles the quadratic computational complexity of Vision Transformers by proposing a frequency-aware token reduction strategy that partitions tokens into high-frequency and low-frequency categories, preserving the former and aggregating the latter into a compact token to mitigate rank collapsing and over-smoothing, resulting in improved accuracy and reduced computational overhead.
Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction methods have been widely explored. However, existing approaches often overlook the frequency characteristics of self-attention, such as rank collapsing and over-smoothing phenomenon. In this paper, we propose a frequency-aware token reduction strategy that improves computational efficiency while preserving performance by mitigating rank collapsing. Our method partitions tokens into high-frequency tokens and low-frequency tokens. high-frequency tokens are selectively preserved, while low-frequency tokens are aggregated into a compact direct current token to retain essential low-frequency components. Through extensive experiments and analysis, we demonstrate that our approach significantly improves accuracy while reducing computational overhead and mitigating rank collapsing and over smoothing. Furthermore, we analyze the previous methods, shedding light on their implicit frequency characteristics and limitations.