Multi-layer Representation Learning for Robust OOD Image Classification
This work addresses the need for trustworthy predictions on unseen data in real-world applications, but it is incremental as it builds on existing methods like Hypercolumns.
The paper tackled the problem of maintaining high accuracy across datasets for image classification by proposing to extract features from intermediate layers of a CNN, specifically adapting the Hypercolumns method to a ResNet-18, resulting in a significant increase in accuracy on the NICO dataset.
Convolutional Neural Networks have become the norm in image classification. Nevertheless, their difficulty to maintain high accuracy across datasets has become apparent in the past few years. In order to utilize such models in real-world scenarios and applications, they must be able to provide trustworthy predictions on unseen data. In this paper, we argue that extracting features from a CNN's intermediate layers can assist in the model's final prediction. Specifically, we adapt the Hypercolumns method to a ResNet-18 and find a significant increase in the model's accuracy, when evaluating on the NICO dataset.