OpenViewer: Openness-Aware Multi-View Learning

Authors: Shide Du, Zihan Fang, Yanchao Tan, Changwei Wang, Shiping Wang, Wenzhong Guo

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments and Studies Datasets, Compared Methods, and Evaluation Metric. We conduct experiments in challenging open-environment classification tasks under six well-known multi-view datasets.
Researcher Affiliation Academia 1 College of Computer and Data Science, Fuzhou University, Fuzhou, China 2 Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou, China 3 Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology, Jinan, China
Pseudocode Yes Open Viewer can be summarized as Algorithm 1 in Appendix.
Open Source Code Yes Code https://github.com/dushide/Open Viewer
Open Datasets Yes We conduct experiments in challenging open-environment classification tasks under six well-known multi-view datasets. This includes two scenarios: 1) Animals, AWA, NUSWIDEOBJ, and VGGFace2-50 datasets contain different manual and deep features; 2) ESP-Game and NUSWIDE20k datasets include various vision and language features. The statistics of these datasets are summarized in Table 1 (details in Appendix).
Dataset Splits Yes Meanwhile, the dataset is partitioned as follows: 10% of the known class samples are allocated for training, another 10% for validation, and the rest 80% for testing.
Hardware Specification Yes Open Viewer is implemented using the Py Torch on an NVIDIA Ge Force RTX 4080 GPU with 16GB of memory.
Software Dependencies No The paper mentions "Py Torch" as a software used, but does not specify a version number or other software dependencies with versions.
Experiment Setup Yes We train Open Viewer for 100 epochs with a batch size of 50, a learning rate of 0.01, ξ = 5, and λ1 and λ2 selected from {10 3, 5 10 3, , 100}.