Suppressing the Heterogeneity: A Strong Feature Extractor for Few-shot Segmentation

Authors: Zhengdong Hu, Yifan Sun, Yi Yang

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

Reproducibility Variable Result LLM Response
Research Type Experimental 4 EXPERIMENTS
Researcher Affiliation Collaboration 1 Re LER, Centre for Artificial Intelligence, University of Technology Sydney, Australia 2 Baidu Inc. 3 CCAI, College of Computer Science and Technology, Zhejiang University
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper states "The Mu HS is reproducible" and describes implementation details, but does not provide an explicit statement about releasing open-source code or a link to a repository.
Open Datasets Yes We evaluate the proposed Mu HS on two datasets: PASCAL-5i (Shaban et al. (2017)) and COCO20i (Nguyen & Todorovic (2019)).
Dataset Splits Yes We divide 20 classes into 4 splits and each split has 5 classes. During evaluation on one split (5 classes), we have other three splits (15 classes) for training. We randomly sample 1000 pairs of support and query in each split testing.
Hardware Specification Yes The proposed Mu HS is trained on Pytorch with 4 NVIDIA A100 GPUS.
Software Dependencies No The paper mentions "Pytorch" but does not specify its version or any other software dependencies with version numbers.
Experiment Setup Yes We use SGD optimizer and set the learning rate as 9e-4. We randomly crop images to 480 480 and follow the data augmentation in PFENet (Tian et al. (2020b)). For PASCAL-5i, we train 50 epochs with batch size 4. For COCO-20i, we train 30 epochs and set batch size to 16.