Weak-shot Semantic Segmentation via Dual Similarity Transfer

Authors: Junjie Chen, Li Niu, Siyuan Zhou, Jianlou Si, Chen Qian, Liqing Zhang

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments on the challenging COCO-Stuff-10K and ADE20K datasets demonstrate the effectiveness of our method.
Researcher Affiliation Collaboration Junjie Chen1, Li Niu1 , Siyuan Zhou1, Jianlou Si2, Chen Qian2, Liqing Zhang1 1The Mo E Key Lab of AI, CSE department, Shanghai Jiao Tong University 2Sense Time Research, Sense Time
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Codes are available at https://github.com/bcmi/Sim Former-Weak-Shot-Semantic-Segmentation.
Open Datasets Yes Comprehensive experiments on the challenging COCO-Stuff-10K and ADE20K datasets demonstrate the effectiveness of our method. [...] COCO-Stuff10K [3] contains 9k training images and 1k test images, covering 171 semantic classes. ADE20K [50] has 20k training images and 2k validating images, covering 150 semantic classes.
Dataset Splits Yes COCO-Stuff10K [3] contains 9k training images and 1k test images, covering 171 semantic classes. ADE20K [50] has 20k training images and 2k validating images, covering 150 semantic classes.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup Yes We use α (0.1 by default) for balancing the distillation loss and β (0.2 by default) for balancing the complementary loss.