Active Boundary Loss for Semantic Segmentation

Authors: Chi Wang, Yunke Zhang, Miaomiao Cui, Peiran Ren, Yin Yang, Xuansong Xie, Xian-Sheng Hua, Hujun Bao, Weiwei Xu2397-2405

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.
Researcher Affiliation Collaboration Chi Wang1,2, Yunke Zhang1,2, Miaomiao Cui2, Peiran Ren2, Yin Yang3, Xuansong Xie2, Xian-Sheng Hua2, Hujun Bao1, Weiwei Xu1* 1 State Key Lab of CAD&CG, Zhejiang University 2Alibaba Inc 3 Clemson University
Pseudocode No The paper describes procedural steps in text, such as 'Phase I' and 'Phase II' of the Active Boundary Loss, but does not present them in a structured pseudocode or algorithm block format.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the methodology described.
Open Datasets Yes We evaluate our loss mainly on the image segmentation dataset Cityscapes (Cordts et al. 2016) and ADE20K (Zhou et al. 2017).
Dataset Splits Yes ADE20K: There are 20210/2000/3000 images for the training/validation/testing set in ADE20K, respectively.
Hardware Specification Yes We implemented the ABL on a GPU server (2 Intel Xeon Gold 6148 CPUs, 512GB memory) with 4 Nvidia Tesla V100 GPUs.
Software Dependencies No The paper mentions software like 'Pytorch' and 'scipy.ndimage.morphology.distance transform edt' but does not specify their version numbers.
Experiment Setup Yes ADE20K: the parameters are set as follows: initial learning rate = 0.02, weight decay = 0.0001, crop size = 520 520, batch size = 16, and 150k training iterations... Cityscapes: the parameters are set as follows: initial learning rate = 0.01 or 0.04, crop size = 512 1024 (used in OCR) or 769 769 (used in Deeplab V3), weight decay = 0.0005, batch size = 8, and 80K training iterations.