Shortcut Learning Susceptibility in Vision Classifiers
Track: regular paper (up to 6 pages)
Keywords: Shortcut Learning, Spurious Correlations, Network Inversion, Reconstructions
TL;DR: This paper evaluates shortcut learning susceptibility in MLPs, CNNs, and ViTs across multiple datasets, showing that ViTs are the most vulnerable to shortcuts while CNNs are the least and higher learning rates reinforce shortcut reliance.
Abstract: Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust and generalizable models. This phenomenon is prevalent across various machine learning applications, including vision, natural language processing, and speech recognition, where models may find unintended cues that minimize training loss but fail to capture the underlying structure of the data. Vision classifiers based on Convolutional Neural Networks (CNNs), Multi-Layer Perceptrons (MLPs), and Vision Transformers (ViTs) leverage distinct architectural principles to process spatial and structural information, making them differently susceptible to shortcut learning. In this study, we systematically evaluate these architectures by introducing deliberate shortcuts into the dataset that are correlated with class labels both positionally and via intensity, creating a controlled setup to assess whether models rely on these artificial cues or learn actual distinguishing features. We perform both quantitative evaluation by training on the shortcut-modified dataset and testing on two different test sets—one containing the same shortcuts and another without them—to determine the extent of reliance on shortcuts. Additionally, qualitative evaluation is performed using network inversion-based reconstruction techniques to analyze what the models internalize in their weights, aiming to reconstruct the training data as perceived by the classifiers. Further, we evaluate susceptibility to shortcut learning across different learning rates. Our analysis reveals that CNNs at lower learning rates tend to be more reserved against entirely picking up shortcut features, while ViTs, particularly those without positional encodings, almost entirely ignore the distinctive image features in the presence of shortcuts.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Presenter: ~Pirzada_Suhail1
Format: Yes, the presenting author will attend in person if this work is accepted to the workshop.
Funding: Yes, the presenting author of this submission falls under ICLR’s funding aims, and funding would significantly impact their ability to attend the workshop in person.
Submission Number: 20
Loading