Semantic Self-adaptation: Enhancing Generalization with a Single Sample
This addresses the critical weakness of deep networks in semantic segmentation for real-world applications where training and test data differ, though it is incremental as it combines existing techniques.
The paper tackles the problem of poor out-of-domain generalization in deep networks for semantic segmentation by introducing a self-adaptive approach that adjusts model parameters during inference for each input sample, achieving new state-of-the-art accuracy on synthetic-to-real benchmarks.
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain fixed at test time. In this work, we challenge this premise with a self-adaptive approach for semantic segmentation that adjusts the inference process to each input sample. Self-adaptation operates on two levels. First, it fine-tunes the parameters of convolutional layers to the input image using consistency regularization. Second, in Batch Normalization layers, self-adaptation interpolates between the training and the reference distribution derived from a single test sample. Despite both techniques being well known in the literature, their combination sets new state-of-the-art accuracy on synthetic-to-real generalization benchmarks. Our empirical study suggests that self-adaptation may complement the established practice of model regularization at training time for improving deep network generalization to out-of-domain data. Our code and pre-trained models are available at https://github.com/visinf/self-adaptive.