Exploring Channel-Aware Typical Features for Out-of-Distribution Detection

Authors: Rundong He, Yue Yuan, Zhongyi Han, Fan Wang, Wan Su, Yilong Yin, Tongliang Liu, Yongshun Gong

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments verify the effectiveness and generalization of LAPS under different architectures and OOD scores.
Researcher Affiliation Academia 1Shandong University 2 Mohamed bin Zayed University of Artificial Intelligence 3 The University of Sydney
Pseudocode No The paper describes the proposed method using mathematical equations and textual explanations, but it does not include a formal pseudocode block or algorithm.
Open Source Code Yes Code is available at: https://github.com/rm1972/LAPS.git.
Open Datasets Yes We use CIFAR-100 (Krizhevsky and Hinton 2009) as ID data for small-scale OOD detection benchmark.
Dataset Splits No The paper mentions 'training set' and 'test set' but does not explicitly specify the proportions or methodology for validation splits.
Hardware Specification No The paper does not provide specific details on the hardware used to run the experiments.
Software Dependencies No The paper does not specify software dependencies with version numbers, such as specific programming languages, libraries, or frameworks used for implementation.
Experiment Setup Yes LAPS has three important hyper-parameters (including λ, m, and n). Here, we empirically show the influence of the hyperparameter λ in Fig. 5(a).