Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection
Authors: Zhiqiang Wu, Yingjie Liu, Hanlin Dong, Xuan Tang, Jian Yang, Bo Jin, Mingsong Chen, Xian Wei
ICLR 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results demonstrate the effectiveness of the proposed R2GConv in natural image classification, and R2Det achieves excellent performance in 2D object detection with improved generalization capabilities and robustness. The code is available in https://github.com/wuer5/r2det. |
| Researcher Affiliation | Academia | 1 Software Engineering Institute, East China Normal University 2 School of Communication and Electronic Engineering, East China Normal University 3 School of Geospatial Information, Information Engineering University 4 School of Computer Science and Technology, Tongji University |
| Pseudocode | Yes | Algorithm 1 Build R2EFilter based on Cn. |
| Open Source Code | Yes | The code is available in https://github.com/wuer5/r2det. |
| Open Datasets | Yes | To investigate the effectiveness of our method, we conduct extensive experiments on the MSCOCO 2017 (COCO) and PASCAL VOC07+12 (VOC) datasets. [...] Image classification. [...] on CIFAR-10 / 100 datasets. |
| Dataset Splits | Yes | Specifically, we manipulate the training set by randomly rotating 60, 000 images by 0, 90, 180, and 270 degrees while maintaining 10, 000 images unaltered in the test set to evaluate the performance of a model under rotation. |
| Hardware Specification | Yes | Both models are trained for 50 epochs with the resized input size 224 224 on dual 4090 GPUs. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | Yes | Table 10: Hyper-parameter settings of R2Det. Table 11: Hyper-parameter settings of R2Net. |