Bottom-up and Top-down: Bidirectional Additive Net for Edge Detection

Authors: Lianli Gao, Zhilong Zhou, Heng Tao Shen, Jingkuan Song

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that our proposed method can improve the edge detection performance to new records and achieve state-of-the-art results on two public benchmarks: BSDS500 and NYUDv2. The ablation study also verifies the effect of each component.
Researcher Affiliation Academia Lianli Gao , Zhilong Zhou , Heng Tao Shen and Jingkuan Song Center for Future Media and School of Computer Science and Technology, University of Electronic Science and Technology of China lianli.gao@uestc.edu.cn, {zhilong.zhou1996, jingkuan.song}@gmail.com, shenhengtao@hotmail.com
Pseudocode No The paper describes the proposed architecture and modules in text and diagrams (Figure 4, Figure 5) but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access information (e.g., a specific repository link, an explicit code release statement) for the source code of the described methodology.
Open Datasets Yes To evaluate our proposed method, we use two commonly used benchmark datasets: BSDS500 [Arbelaez et al., 2011] and NYUDv2 [Silberman et al., 2012].
Dataset Splits Yes Follow [Xie and Tu, 2017] [Liu et al., 2019], we train our network on training and validation sets and test our method on test set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions using VGG16 pre-trained on ImageNet and SGD optimization, but does not provide specific version numbers for any software components, libraries, or frameworks.
Experiment Setup Yes The hyper-parameter λd in Equation 10 is set as 300. The C, N and L are set to 21, 2 and 5 in Section 2. Following [Liu et al., 2019], λ is set to 1.1 for BSDS500 and 1.2 for NYUDv2 respectively. We employ SGD optimization during training. The learning rate, weight decay, momentum and batch size are set to 1e-7, 0.9, 2e-4 and 10, respectively. We train BSDS500 for 15k steps and NYUDv2 for 30k steps because of the different sizes of training set.