3D shape recognition has been actively investigated in the field of computer graphics. With the rapid development of deep learning, various deep models have been introduced and achieved remarkable results. Most 3D shape recognition methods are supervised and learn only from the large amount of labeled shapes. However, it is expensive and time consuming to obtain such a large training set. In contrast to these methods, this paper studies a semi-supervised learning framework to train a deep model for 3D shape recognition by using both labeled and unlabeled shapes. Inspired by the co-training algorithm, our method iterates between model training and pseudo-label generation phases. In the model training phase, we train two deep networks based on the point cloud and multi-view representation simultaneously. In the pseudo-label generation phase, we generate the pseudo-labels of the unlabeled shapes using the joint prediction of two networks, which augments the labeled set for the next iteration. To extract more reliable consensus information from multiple representations, we propose an uncertainty-aware consistency loss function to combine the two networks into a multimodal network. This not only encourages the two networks to give similar predictions on the unlabeled set, but also eliminates the negative influence of the large performance gap between the two networks. Experiments on the benchmark ModelNet40 demonstrate that, with only 10% labeled training data, our approach achieves competitive performance to the results reported by supervised methods.
The collection of signature data for system development and evaluation generally requires significant time and effort. To overcome this problem, this paper proposes a detector generation based clonal selection algorithm for synthetic signature set generation. The goal of synthetic signature generation is to improve the performance of signature verification by providing more training samples. Our method uses the clonal selection algorithm to maintain the diversity of the overall set and avoid sparse feature distribution. The algorithm firstly generates detectors with a segmentedr-continuous bits matching rule andP-receptor editing strategy to provide a more wider search space. Then the clonal selection algorithm is used to expand and optimize the overall signature set. We demonstrate the effectiveness of our clonal selection algorithm, and the experiments show that adding the synthetic training samples can improve the performance of signature verification.
The artificial bee colony (ABC) algorithm is a recently introduced swarm intelligence optimization algorithm based on the foraging behavior of a honeybee colony. However, many problems are encountered in the ABC algorithm, such as premature convergence and low solution precision. Moreover, it can easily become stuck at local optima. The scout bees start to search for food sources randomly and then they share nectar information with other bees. Thus, this paper proposes a global reconnaissance foraging swarm optimization algorithm that mimics the intelligent foraging behavior of scouts in nature. First, under the new scouting search strategies, the scouts conduct global reconnaissance around the assigned subspace, which is effective to avoid premature convergence and local optima. Second, the scouts guide other bees to search in the neighborhood by applying heuristic information about global reconnaissance. The cooperation between the honeybees will contribute to the improvement of optimization performance and solution precision. Finally, the prediction and selection mechanism is adopted to further modify the search strategies of the employed bees and onlookers. Therefore, the search performance in the neighborhood of the local optimal solution is enhanced. The experimental results conducted on 52 typical test functions show that the proposed algorithm is more effective in avoiding premature convergence and Communicated by improving solution precision compared with some other ABCs and several state-of-the-art algorithms. Moreover, this algorithm is suitable for optimizing high-dimensional space optimization problems, with very satisfactory outcomes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.