Rethinking Object Detection in Retail Stores
Authors: Yuanqiang Cai, Longyin Wen, Libo Zhang, Dawei Du, Weiqiang Wang947-954
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments are conducted on the proposed dataset to demonstrate its significance and the analysis is provided to indicate future directions. As presented in Table 2, we compare our CLCNet method with the state-of-the-art object detectors... |
| Researcher Affiliation | Collaboration | Yuanqiang Cai1,2 , Longyin Wen3 , Libo Zhang1,2 , Dawei Du4, Weiqiang Wang2 1State Key Laboratory of Computer Science, ISCAS, China 2University of Chinese Academy of Sciences, China 3Bytedance Inc., Mountain View, USA 4University at Albany, SUNY, USA |
| Pseudocode | No | The paper describes the architecture and logic of its proposed CLCNet, but it does not include a dedicated pseudocode block or an algorithm figure. |
| Open Source Code | No | The paper provides a link for the dataset ('https://isrc.iscas.ac.cn/gitlab/research/locount-dataset'), but it does not provide an explicit statement or link for the open-source code of their proposed methodology (CLCNet). |
| Open Datasets | Yes | Dataset is available at https://isrc.iscas.ac.cn/gitlab/research/locount-dataset. |
| Dataset Splits | No | The paper states: 'To facilitate data usage, we divide the dataset into two subsets, i.e., training and testing sets, including 34, 022 images for training and 16, 372 images for testing.' It explicitly defines training and testing sets but does not mention a separate validation set for their own dataset. |
| Hardware Specification | Yes | All the experiments are conducted on a machine with 1 NVIDIA Titan Xp GPU and a 2.80GHz Intel(R) Xeon(R) E5-1603 v4 processor. |
| Software Dependencies | No | The paper mentions that 'All the evaluated methods are implemented based on the mmdetection platform3' and provides a GitHub link for mmdetection, but it does not specify concrete version numbers for mmdetection itself or other key software dependencies like Python, PyTorch, or CUDA. |
| Experiment Setup | Yes | The batch size is set to 8 in the training phase. The whole network is trained using the stochastic gradient descent (SGD) algorithm with the 0.9 momentum and 0.0001 weight decay. The initial learning rate is set to 0.02. We set the incremental parameter vl of the localization Io U threshold for positive/negation sample generation to 0.05 for six stages and 0.2 for two stages. The predefined parameters λ1 and λ2 in the loss function are set to 1.0 and 0.0001 for the count-regression strategy, and set to 1.0 and 0.1 for the count-classification strategy. |