Adaptive Pattern-Parameter Matching for Robust Pedestrian Detection
Authors: Mengyin Liu, Chao Zhu, Jun Wang, Xu-Cheng Yin2154-2162
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on two popular benchmarks, Caltech and City Persons, show that our proposed method achieves superior performance compared to other state-of-the-art methods on subsets of different scales and occlusion types. |
| Researcher Affiliation | Academia | Mengyin Liu, Chao Zhu*, Jun Wang, Xu-Cheng Yin* School of Computer and Communication Engineering University of Science and Technology Beijing, Beijing, China blean@live.cn, chaozhu@ustb.edu.cn, wj fm0604@foxmail.com, xuchengyin@ustb.edu.cn |
| Pseudocode | No | The paper describes modules and their functions but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any links to open-source code or explicit statements about code availability. |
| Open Datasets | Yes | The Caltech pedestrian dataset (Doll ar et al. 2009) contains 2.5 hours of video data... City Persons (Zhang, Benenson, and Schiele 2017) is a recently published large-scale pedestrian detection dataset. |
| Dataset Splits | Yes | The standard test set includes 4024 images. We train the model on an official training set with 2975 images and test it on validation set with 500 images. |
| Hardware Specification | Yes | For Caltech dataset, one Nvidia P100 GPU is utilized for training. For City Persons, two P40 GPUs are applied to training. All the tests are conducted on a single 1080Ti GPU. |
| Software Dependencies | No | The paper mentions 'Keras framework' and 'Adam' but does not specify version numbers for these software dependencies. |
| Experiment Setup | Yes | For Caltech dataset, ... with 1 × 10−4 learning rate. For City Persons, ... with 2 × 10−4 learning rate. The size of training images is 336 × 448 for Caltech and 640 × 1280 for City Persons. For the best ensemble, IoU threshold of NMS after fusing detection results of two policies are 0.54 for Caltech and 0.59 for City Persons. |