Weakly-Supervised Audio-Visual Segmentation

Authors: Shentong Mo, Bhiksha Raj

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on AVSBench demonstrate the effectiveness of our WS-AVS in the weakly-supervised audio-visual segmentation of single-source and multi-source scenarios.
Researcher Affiliation Academia Shentong Mo1,2 Bhiksha Raj1,2 1CMU, 2MBZUAI
Pseudocode No The paper describes its method using text and equations but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement about releasing source code for the described methodology, nor does it include a link to a code repository.
Open Datasets Yes AVSBench [1] contains 4,932 videos with 10,852 total frames from 23 categories including animals, humans, instruments, etc. Following prior work [1], we use the split of 3,452/740/740 videos for train/val/test in single source segmentation.
Dataset Splits Yes Following prior work [1], we use the split of 3,452/740/740 videos for train/val/test in single source segmentation.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions using the Adam optimizer but does not provide specific version numbers for any software dependencies or libraries used in the experiments.
Experiment Setup Yes The model is trained with the Adam optimizer with default hyper-parameters β1 = 0.9, β2 = 0.999, and a learning rate of 1e-4. The model is trained for 20 epochs with a batch size of 64.