This is the authors' abstract. We don't add key points for this paper.
Batch normalization (BN) has become a foundational component in modern deep neural networks. However, one of its disadvantages is its reliance on batch statistics that may be unreliable or unavailable during inference, particularly under test-time domain shifts. While batch-statistics-free affine transformation methods alleviate this by learning per-sample scale and shift parameters, most treat samples independently, overlooking temporal or sequential correlations in streaming or episodic test-time settings. We propose LSTM-Affine, a memory-based normalization module that replaces BN with a recurrent parameter generator. By leveraging an LSTM, the module produces channel-wise affine parameters conditioned on both the current input and its historical context, enabling gradual adaptation to evolving feature distributions. Unlike conventional batch-statistics-free designs, LSTM-Affine captures dependencies across consecutive samples, improving stability and convergence in scenarios with gradual distribution shifts. Extensive experiments on few-shot learning and source-free domain adaptation benchmarks demonstrate that LSTM-Affine consistently outperforms BN and prior batch-statistics-free baselines, particularly when adaptation data are scarce or non-stationary.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Yeh et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: