Learning Spatial Similarity Distribution for Few-shot Object Counting

Authors: Yuanwu Xu, Feifan Song, Haofeng Zhang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct comprehensive experiments on two renowned public benchmark datasets, i.e., FSC-147 [Ranjan et al., 2021] and CARPK [Hsieh et al., 2017]. The results clearly illustrate that our approach surpasses the performance of current state-of-the-art methods.
Researcher Affiliation Academia Yuanwu Xu , Feifan Song , Haofeng Zhang School of Artificial Intelligence, Nanjing University of Science and Technology {xuyuanwu, sff, zhanghf}@njust.edu.cn
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code Yes Code is available at https://github.com/CBalance/SSD.
Open Datasets Yes FSC-147 is a comprehensive multi-class few-shot object counting dataset. It comprises a total of 6,135 images covering 89 distinct object categories. ... To facilitate experimentation, the dataset is further divided into training, validation, and testing subsets, with each subset containing 29 non-overlapping object categories. CARPK is a class-specific car counting dataset, which consists of 1448 images of parking lots from a bird s view. ... The training set comprises three scenes, while a separate scene is designated for test.
Dataset Splits Yes To facilitate experimentation, the dataset is further divided into training, validation, and testing subsets, with each subset containing 29 non-overlapping object categories.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments (e.g., GPU models, CPU types, or memory).
Software Dependencies No The paper mentions 'Adam W' as the optimizer but does not specify version numbers for any software libraries, frameworks (e.g., PyTorch, TensorFlow), or programming languages.
Experiment Setup Yes We apply Adam W [Loshchilov and Hutter, 2017] as the optimizer with a learning rate of 1 10 4 and the learning rate decays with a rate of 0.95 after each epoch. The batch size is 4 and the model is trained for 100 epochs. ... γ and η in DIS method are set to 32 and 12.