Shape-Guided Dual-Memory Learning for 3D Anomaly Detection

Authors: Yu-Min Chu, Chieh Liu, Ting-I Hsieh, Hwann-Tzong Chen, Tyng-Luh Liu

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate our method on MVTec 3DAD (Bergmann & Sattlegger, 2022), which provides ten different categories of 3D objects for 2D+3D anomaly detection.
Researcher Affiliation Collaboration 1Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan 2Aeolus Robotics, Taipei, Taiwan 3Institute of Information Science, Academia Sinica, Taipei, Taiwan.
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include an unambiguous statement about releasing source code for the described methodology or a direct link to a code repository.
Open Datasets Yes We evaluate our method on MVTec 3DAD (Bergmann & Sattlegger, 2022), which provides ten different categories of 3D objects for 2D+3D anomaly detection.
Dataset Splits Yes MVTec 3D-AD contains 2,656 training, 294 validation, and 1,197 test samples.
Hardware Specification Yes Table 3. Comparison of inference time (second) per sample, frame per second (FPS), the number of features (No F), and the percentage of RGB memory usage on an Nvidia GTX 1080 GPU.
Software Dependencies No The paper mentions software components like "Point Net", "NIF", "Image Net pretrained Res Net", "Wide Res Net-50-2", and "Patch Core" but does not provide specific version numbers for any of them.
Experiment Setup Yes We set the learning rate and batch size to 0.0001 and 32, respectively, which empirically achieves efficient convergence.