All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

Authors: Liyao Tang, Zhe Chen, Shanshan Zhao, Chaoyue Wang, Dacheng Tao

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

Reproducibility Variable Result LLM Response
Research Type Experimental We validate the effectiveness through extensive experiments on various baselines and large-scale datasets. Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings.
Researcher Affiliation Academia 1 The University of Sydney, Australia 2 La Trobe University, Australia
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper.
Open Source Code No Code and model will be made publicly available at https://github.com/Liyao Tang/ERDA. Our code and pre-trained models will be released.
Open Datasets Yes We experiment with multiple large-scale datasets, including S3DIS [2], Scan Net [16], Sensat Urban [33] and Pascal [19].
Dataset Splits Yes For a fair comparison, we follow previous works [94, 95, 32] and experiment with different settings, including the 0.02% (1pt), 1% and 10% settings, where the available labels are randomly sampled according to the ratio3. We also conduct the 6-fold cross-validation, as reported in Tab. 3.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running experiments were provided in the paper.
Software Dependencies No No specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9, CUDA 11.1) needed to replicate the experiment were provided in the paper.
Experiment Setup Yes we use 2-layer MLPs for the projection network g and set m = 0.999. For training, we follow the setup of the baselines and set the loss weight α = 0.1.