Localization with Sampling-Argmax

Authors: Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-Lu Li, Cewu Lu

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate the benefits of the proposed sampling-argmax with experiments on a variety of localization tasks, including human pose estimation, retina segmentation and object keypoint estimation.
Researcher Affiliation Academia Jiefeng Li Tong Chen Ruiqi Shi Yujing Lou Yong-Lu Li Cewu Lu Shanghai Jiao Tong University {ljf_likit,chentong1023, gzfoxie, louyujing, yonglu_li, lucewu}@sjtu.edu.cn
Pseudocode No The paper does not include a dedicated section or figure explicitly labeled "Pseudocode" or "Algorithm".
Open Source Code Yes Code is available at https://github.com/Jeff-sjtu/sampling-argmax.
Open Datasets Yes The experiments are conducted on the large-scale in-the-wild 2D human pose benchmark COCO Keypoint [19]. We further evaluate the proposed sampling-argmax on Human3.6M [10], an indoor benchmark for 3D human pose estimation.
Dataset Splits No While the paper states "Training details of all tasks are provided in the supplemental material," it does not explicitly provide the specific training/validation/test splits within the main body of the paper.
Hardware Specification Yes The required training resources (number of GPUs) are elaborated in the supplemental material.
Software Dependencies No The paper states "Training details of all tasks are provided in the supplemental material," but does not explicitly list specific software dependencies with version numbers in the main text.
Experiment Setup Yes In our experiment, we tune the loss weight ranging from 0.1 to 10 and the variance ranging from 1 to 5 for each task.