Unsupervised Day–Night Domain Adaptive Image Classification Based on Target-Domain Discriminative Enhancement

Day–night image classification under low-light conditions faces substantial domain shift, uncertain target-domain predictions, and unreliable pseudo-label supervision. To address these challenges, this paper proposes an unsupervised day–night domain adaptation method for image classification based on target-domain discriminative enhancement. Built on a bidirectional day–night domain alignment framework, the method introduces Target-Domain Discriminative Clustering (TDCL) and Confidence-Calibrated Pseudo-Label Learning (ConCal). TDCL combines sample-level entropy minimization with batch-level nuclear-norm maximization to improve prediction certainty and the discriminative structure of target-domain predictions. ConCal applies class-adaptive confidence thresholds to current-model predictions to select reliable target samples and uses the corresponding pseudo-labels for self-training. On the CODaN nighttime test set, the proposed method achieves an accuracy of 76.24 ± 0.41%, exceeding the published WiiD result by 5.92 percentage points. On the extended ExDark evaluation set, comprising additional non-overlapping nighttime images, it achieves 76.73 ± 0.57%, outperforming the reproduced WiiD baseline by 3.63 percentage points. These results indicate that explicitly optimizing the target-domain prediction structure and improving pseudo-label reliability can further enhance nighttime classification.