Learning to Model Pixel-Embedded Affinity for Homogeneous Instance Segmentation
Authors: Wei Huang, Shiyu Deng, Chang Chen, Xueyang Fu, Zhiwei Xiong1007-1015
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate the versatile and superior performance of our method on three representative datasets. |
| Researcher Affiliation | Academia | 1University of Science and Technology of China 2Institute of Artificial Intelligence, Hefei Comprehensive National Science Center |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code and models are available at https://github.com/weih527/ Pixel-Embedded-Affinity. |
| Open Datasets | Yes | The Computer Vision Problems in Plant Phenotyping (CVPPP) dataset (Minervini et al. 2016)... The BBBC039V1 dataset from (Ljosa, Sokolnicki, and Carpenter 2012)... AC3/AC4 are two labeled subsets cropped from the mouse somatosensory cortex dataset of (Kasthuri et al. 2015)... |
| Dataset Splits | Yes | We randomly select 20 images from the training set as the validation set. Following the official data split, we use 100 images for training, 50 for validation and the rest 50 for testing. we adopt the top 80 sections of AC4 as the training set, the remaining 20 sections as the validation set and the top 100 sections of AC3 as the test set. |
| Hardware Specification | Yes | We train these networks using Adam (Kingma and Ba 2015) with β1 = 0.9, β2 = 0.999, a learning rate of 0.0001, and a batch size of 2 on an NVIDIA Titan XP GPU for 200, 000 iterations. |
| Software Dependencies | No | The paper mentions the use of Adam optimizer but does not specify software dependencies like library names with version numbers (e.g., Python, PyTorch, TensorFlow, or CUDA versions). |
| Experiment Setup | Yes | We train these networks using Adam (Kingma and Ba 2015) with β1 = 0.9, β2 = 0.999, a learning rate of 0.0001, and a batch size of 2 on an NVIDIA Titan XP GPU for 200, 000 iterations. The weighting coefficients of the loss function is empirically set as α = β = γ = 1. The number of embedding dimensions is set to 16. |