Fine-Grained ImageNet Classification in the Wild
This work addresses robustness issues in image classifiers for researchers and practitioners, though it is incremental as it extends existing robustness testing to a more realistic setting.
The paper tackled the problem of evaluating model robustness for fine-grained image classification under real-world distribution shifts using uncurated web-crawled data, and the result was an information-rich evaluation scheme that revealed model vulnerabilities and explained misclassifications through hierarchical knowledge.
Image classification has been one of the most popular tasks in Deep Learning, seeing an abundance of impressive implementations each year. However, there is a lot of criticism tied to promoting complex architectures that continuously push performance metrics higher and higher. Robustness tests can uncover several vulnerabilities and biases which go unnoticed during the typical model evaluation stage. So far, model robustness under distribution shifts has mainly been examined within carefully curated datasets. Nevertheless, such approaches do not test the real response of classifiers in the wild, e.g. when uncurated web-crawled image data of corresponding classes are provided. In our work, we perform fine-grained classification on closely related categories, which are identified with the help of hierarchical knowledge. Extensive experimentation on a variety of convolutional and transformer-based architectures reveals model robustness in this novel setting. Finally, hierarchical knowledge is again employed to evaluate and explain misclassifications, providing an information-rich evaluation scheme adaptable to any classifier.