Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time
Authors: Elena Burceanu, Marius Leordeanu
IJCAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In experiments, we obtain consistent improvement over the top state of the art methods on DAVIS-2016 dataset. We also achieve top results on the well-known Seg Trackv2 dataset. |
| Researcher Affiliation | Collaboration | Elena Burceanu1,2 and Marius Leordeanu3,4 1Bitdefender 2University of Bucharest, Romania 3Institute of Mathematics of the Romanian Academy 4University Politehnica of Bucharest, Romania |
| Pseudocode | Yes | Algorithm 1 Power iteration with 3D convolutions algorithm. |
| Open Source Code | No | The paper mentions Pytorch and Flownet2 but does not provide a link or explicit statement for releasing the SFSeg code described in the paper. |
| Open Datasets | Yes | Experiments on DAVIS-2016. DAVIS-2016 [Perazzi et al., 2016] is a densely annotated video object segmentation dataset. |
| Dataset Splits | Yes | DAVIS-2016 [Perazzi et al., 2016] is a densely annotated video object segmentation dataset. It contains 50 high-resolution video sequences (30 train/20 valid), with a total of 3455 annotated frames of real-world scenes. The benchmark comes with two tasks: the unsupervised one, where the solutions do not have access to the first frame of the video and the semi-supervised one, where the methods use the ground-truth from the first frame. In both setups, the methods can train the model on the training set and report their performance on the validation set. Our results are reported on the validation set, but we do not use the training set. |
| Hardware Specification | Yes | We tested on a GTX Titan X Maxwell GPU, in Pytorch [Paszke et al., 2017]. |
| Software Dependencies | No | The paper mentions 'Pytorch implementation of Flownet2 [Reda et al., 2017]' and 'Pytorch [Paszke et al., 2017]', but no specific version numbers for these software components are provided. |
| Experiment Setup | Yes | We set: Ni = 5; α = 1 and p = 0.1 for unsupervised task and p = 0.2 for the semi-supervised one. |