Kernel Orthogonality does not necessarily imply a Decrease in Feature Map Redundancy in CNNs: Convolutional Similarity Minimization
Convolutional Neural Networks (CNNs) have been heavily used in Deep Learning due to their success in various tasks. Nonetheless, it has been observed that CNNs suffer from redundancy in feature maps, leading to inefficient capacity utilization. Efforts to mitigate and solve this problem led to the e...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Convolutional Neural Networks (CNNs) have been heavily used in Deep Learning
due to their success in various tasks. Nonetheless, it has been observed that
CNNs suffer from redundancy in feature maps, leading to inefficient capacity
utilization. Efforts to mitigate and solve this problem led to the emergence of
multiple methods, amongst which is kernel orthogonality through variant means.
In this work, we challenge the common belief that kernel orthogonality leads to
a decrease in feature map redundancy, which is, supposedly, the ultimate
objective behind kernel orthogonality. We prove, theoretically and empirically,
that kernel orthogonality has an unpredictable effect on feature map similarity
and does not necessarily decrease it. Based on our theoretical result, we
propose an effective method to reduce feature map similarity independently of
the input of the CNN. This is done by minimizing a novel loss function we call
Convolutional Similarity. Empirical results show that minimizing the
Convolutional Similarity increases the performance of classification models and
can accelerate their convergence. Furthermore, using our proposed method pushes
towards a more efficient use of the capacity of models, allowing the use of
significantly smaller models to achieve the same levels of performance. |
---|---|
DOI: | 10.48550/arxiv.2411.03226 |