Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

Authors: Ankit Goyal, Kaiyu Yang, Dawei Yang, Jia Deng

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically validate that minimally contrastive examples can diagnose issues with current relation detection models as well as lead to sample-efficient training.
Researcher Affiliation Academia University of Michigan, Ann Arbor, MI Princeton University, Princeton, NJ
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Code and data are available at https://github.com/princeton-vl/Rel3D.
Open Datasets Yes Code and data are available at https://github.com/princeton-vl/Rel3D.
Dataset Splits Yes Hyper-parameters for each model are tuned separately using validation data, and the best-performing model on the validation set is used for testing.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper mentions software like Blender and Unity Web GL but does not specify their version numbers for reproducibility.
Experiment Setup Yes All images are resized to 224 224 before feeding into the model. We perform random cropping and color jittering on training data. Hyper-parameters for each model are tuned separately using validation data, and the best-performing model on the validation set is used for testing.