In view of the problem that traditional resampling methods, which mostly use fixed sampling strategies, cannot change the sampling strategy according to the optimization requirements of the model, this paper proposed an adaptive sampling-based imbalanced classification method (ASIC). This method dynamically adjusts the sampling probabilities of samples of different classes on the training set according to the performance of the classification model on the validation set, so that the sampling probabilities of different classes can be dynamically determined by the requirements of the current classification model. At the same time, this method pays extra attention to the minority classes and gives the minority classes a higher sampling probability under the same other conditions, so as to compensate for the negative impact due to the insufficient number of samples of the minority class and to improve the recognition ability of the model for the minority classes. Experimental results show that this method performs better than the contrasting methods in the geometric mean in terms of both the mean class accuracy and recall. The superiority of the ASIC approach is more obvious when the data distribution is more unbalanced.

Zero-shot image semantic segmentation is one of the important tasks in the visual field of zero-shot learning, aiming to segment novel categories unseen during training. The current distribution of visual features based on pixel-level visual feature generation is inconsistent with real visual feature distribution. The synthesized visual features inadequately reflect class semantic information, leading to low discriminability in these features.Some existing generative methods consume significant computational resources to obtain the discriminative information conveyed by semantic features. In view of the above problems, this paper proposed a zero-shot image semantic segmentation network called SVCCNet, which is based on semantic-visual consistency constraints. SVCCNet uses a semantic-visual consistency constraint module to facilitate the mutual transformation between semantic features and visual features, enhancing their correlation and diminishing the disparity between the spatial structures of real and synthesized visual features, which mitigates the inconsistency problem between the distributions of synthesized and real visual features. The semantic-visual consistency constraint module achieves the correspondence between visual features and class semantics through two mutually constrained reconstruction mappings, while maintaining low model complexity. Experimental results on the PASCAL-VOC and PASCAL-Context datasets demonstrate that SVCCNet outperforms mainstream methods in terms of pixel accuracy, mean accuracy, mean intersection over union (IoU), and harmonic IoU.