Learning Loss for Test-Time Augmentation
This work addresses the need for more efficient and effective test-time augmentation in neural networks, particularly for enhancing robustness in image classification tasks, though it is incremental as it builds on existing augmentation methods.
The paper tackles the problem of selecting appropriate transformations for test-time augmentation by proposing an instance-level method that uses an auxiliary module to predict losses for each transformation, applying those with lower predicted losses and averaging predictions. Experimental results on image classification benchmarks show improved robustness against various corruptions.
Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used for test-time augmentation. This paper proposes a novel instance-level test-time augmentation that efficiently selects suitable transformations for a test input. Our proposed method involves an auxiliary module to predict the loss of each possible transformation given the input. Then, the transformations having lower predicted losses are applied to the input. The network obtains the results by averaging the prediction results of augmented inputs. Experimental results on several image classification benchmarks show that the proposed instance-aware test-time augmentation improves the model's robustness against various corruptions.