In the realm of image classification, the capsule network is a network topology that packs the extracted features into many capsules, performs sophisticated capsule screening using a dynamic routing mechanism, and finally recognizes that each capsule corresponds to a category feature. Compared with previous network topologies, the capsule network has more sophisticated operations, uses a large number of parameter matrices and vectors to express picture attributes, and has more powerful image classification capabilities. However, in the practical application field, the capsule network has always been constrained by the quantity of calculation produced by the complicated structure. In the face of basic datasets, it is prone to over-fitting and poor generalization and often cannot satisfy the high computational overhead when facing complex datasets. Based on the aforesaid problems, this research proposes a novel enhanced capsule network topology. The upgraded network boosts the feature extraction ability of the network by incorporating a multi-scale feature extraction module based on proprietary star structure convolution into the standard capsule network. At the same time, additional structural portions of the capsule network are changed, and a variety of optimization approaches such as dense connection, attention mechanism, and low-rank matrix operation are combined. Image classification studies are carried out on different datasets, and the novel structure suggested in this paper has good classification performance on CIFAR-10, CIFAR-100, and CUB datasets. At the same time, we also achieved 98.21% and 95.38% classification accuracy on two complicated datasets of skin cancer ISIC derived and Forged Face EXP.
The exotic pet trade is a major driver of alien species invasions. Improper introductions or a lack of management can result in severe ecological consequences. Therefore, accurate identification of exotic pets is essential for the prevention and early warning of species invasions. This paper proposes a novel recognition method for fine-grained images of small-scale exotic pet snakes in complex backgrounds based on an improved SimCLR framework. A hierarchical window attention mechanism is introduced into the encoder network to enhance feature extraction. In the loss function, a supervised contrastive mechanism is introduced to exclude false negative samples using label information, which helps reduce representation noise and enhance training stability. The training strategy incorporates random erasing and random grayscale data augmentation techniques to improve performance further. The projection head is constructed using a two-layer multilayer perceptron (MLP), and the cosine annealing schedule combined with the AdamW optimizer is adopted for learning rate adjustment. Experimental results on a self-constructed dataset demonstrate that the proposed model achieves a recognition accuracy of 97.5%, outperforming existing baseline models. This study fills a gap in exotic pet snake classification and provides a practical tool for species invasion prevention and early detection.
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.