Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters

Authors: Zheng Wu, Ruiheng Chang, Jiaxu Ma, Cewu Lu, Chi Keung Tang

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments and comparisons are performed to verify our method. We build a dataset consisting of pixel-level annotated images of HOC.
Researcher Affiliation Academia 1 Shanghai Jiao Tong University 2 HKUST
Pseudocode No The paper describes algorithmic steps in paragraph form but does not contain a structured pseudocode or clearly labeled algorithm block.
Open Source Code No The dataset and codes will be released.
Open Datasets Yes We build a dataset consisting of pixel-level annotated images of HOC. The dataset and codes will be published with the paper.
Dataset Splits No The paper mentions evaluating using COCO metrics and provides total instance count for their custom dataset, but it does not specify explicit training, validation, and test splits (e.g., percentages or sample counts) for their custom dataset.
Hardware Specification Yes on four Titan X GPU.
Software Dependencies No The paper mentions using Mask R-CNN and fine-tuning VGG-16 and AlexNet models, but it does not provide specific version numbers for software dependencies or libraries.
Experiment Setup Yes We finetune the model for 30,000 iterations with a learning rate of 0.001, minibatch size of 32, momentum of 0.9 and weight decay of 0.01.