Mean-Shifted Contrastive Loss for Anomaly Detection

Authors: Tal Reiss, Yedid Hoshen

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrating the state-of-the-art anomaly detection performance of our method (e.g. 98.6% ROC-AUC on CIFAR-10).
Researcher Affiliation Academia Tal Reiss, Yedid Hoshen The Hebrew University of Jerusalem
Pseudocode No The paper contains mathematical equations but does not include explicitly labeled 'Pseudocode' or 'Algorithm' blocks, nor does it present structured steps in a code-like format.
Open Source Code Yes Full training and implementation details are in the Supplementary Material1. 1https://github.com/talreiss/Mean-Shifted-Anomaly-Detection
Open Datasets Yes We evaluated our approach on a wide range of anomaly detection benchmarks. Following (Golan and El-Yaniv 2018; Hendrycks et al. 2019), we run our experiments on commonly used datasets: CIFAR-10 (Krizhevsky, Hinton et al. 2009), CIFAR-100 coarse-grained version that consists of 20 classes (Krizhevsky, Hinton et al. 2009), and Cats Vs Dogs (Elson et al. 2007).
Dataset Splits No The paper mentions 'training set of normal samples' and 'normal training images' but does not explicitly provide specific percentages, sample counts, or methodology for train/validation/test splits for reproducibility.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or cloud computing instances used for running the experiments.
Software Dependencies No The paper does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions) that would be needed to replicate the experiments.
Experiment Setup No The paper mentions fine-tuning with Lmsc and using ResNet152 but states 'Full training and implementation details are in the Supplementary Material' without providing specific hyperparameters such as learning rate, batch size, or number of epochs within the main text.