DNA triple helix structure, as a highly specific gene targeting tool, enable gene regulation by precisely identifying and binding to target DNA sequences. However, the limits of design quality and efficiency affect th...
详细信息
Pathological myopia has become an important cause of blindness, and automatic recognition of pathological myopia by computer is significance for reducing the risk of blindness. In order to assist doctors to improve th...
详细信息
Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ig...
详细信息
Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.
Pre-trained Language Models have been shown to be able to emulate deductive reasoning in natural language. However, PLMs are easily affected by irrelevant information (e.g., entity) in instance-level proofs when learn...
详细信息
The complexity and diversity of smart grid systems increase the likelihood of anomalies in communications between devices in the system, and how these anomalies are detected is critical to the security of the grid sys...
详细信息
Aiming at the low matching accuracy of existing local stereo matching algorithms in weak texture areas, a local stereo matching algorithm based on multi-matching cost fusion and guided filtering cost aggregation with ...
详细信息
Recently, graph neural networks(GNNs) have played a key crucial in many recommendation situations. In particular, contrastive learning-based hypergraph neural networks (HGNNs) are gradually becoming a research focus f...
详细信息
The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage ...
详细信息
Concept drift refers to the probability distribution of data generation changes over time in a data stream environment. In recent years, there has been an increasing interest in drift detection models. However, due to...
In the context of edge computing environments, where the storage space and computational resources are constrained, complex super-resolution network models face significant challenges during inference. In this paper, ...
详细信息
暂无评论