Domain-General Crowd Counting in Unseen Scenarios
Authors: Zhipeng Du, Jiankang Deng, Miaojing Shi
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on several standard crowd counting benchmarks i.e. SHA, SHB, QNRF, and NWPU, show the strong generalizability of our method. Our code is available at: https://github.com/ZPDu/Domaingeneral-Crowd-Counting-in-Unseen-Scenarios |
| Researcher Affiliation | Collaboration | Zhipeng Du2, Jiankang Deng3, Miaojing Shi1,2* 1 College of Electronic and Information Engineering, Tongji University, China 2King s College London, UK 3Huawei London Research Center, UK zhipeng.du@kcl.ac.uk, j.deng16@imperial.ac.uk, mshi@tongji.edu.cn |
| Pseudocode | No | The paper describes the methodology in prose and with diagrams (e.g., Figure 2), but does not include any formal pseudocode blocks or algorithms. |
| Open Source Code | Yes | Our code is available at: https://github.com/ZPDu/Domaingeneral-Crowd-Counting-in-Unseen-Scenarios |
| Open Datasets | Yes | We evaluate our method on three crowd counting datasets: SHTech (Zhang et al. 2016), QNRF (Idrees et al. 2018), NWPU (Wang et al. 2020b). SHTech contains two parts, SHA and SHB; the former is much denser than the latter on average. NWPU and QNRF are two large-scale datasets with diverse crowd scenarios, covering a wide range of crowd densities. We select one dataset as the source domain to train our model on its train set, and evaluate the trained model on the test sets of rest datasets. |
| Dataset Splits | No | The paper mentions training and testing on datasets but does not explicitly detail a validation split or how it's used for hyperparameter tuning or early stopping. It says "Parameters are tuned on the test set of the source domain" which is an unusual practice typically done on a validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for experiments, such as GPU models, CPU types, or memory. |
| Software Dependencies | No | The paper mentions using Adam as optimizer and ReLU as activation functions, but does not list specific software dependencies with version numbers (e.g., PyTorch 1.9, Python 3.8, CUDA 11.1). |
| Experiment Setup | Yes | We use Adam as optimizer with a fixed learning rate of 10 5. We augment training data by randomly cropping patches with a fixed size 320 320 from images and then apply random horizontal flipping. We train the model for 150 epochs, and each contains 100 iterations. In each iteration, we sample one image from each sub-domain and iterate the training by taking one as meta-test image and the rest as meta-train images. Empirically, we apply 3-means clustering to divide sub-domains in SHB and 4-means clustering in SHA and SHA+SHB. For QNRF, we apply 8-means clustering. The numbers of memory vectors M and N are set as 1024 and 256 for DICM and DSCM, respectively. Dimension C is 256. In the hard region reinforcement (Sec. 3.5), we select top S = 2% hard predicted regions over total regions per image. Loss weights λrec and λorth in (4) are set to 0.1 and 0.01, respectively. |