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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification
Authors: Xixi Wan, AIHUA ZHENG, Bo Jiang, Beibei Wang, Chenglong Li, Jin Tang
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | UGG-Re ID is comprehensively evaluated on five representative multi-modal object Re ID datasets, encompassing diverse spectral modalities. Experimental results show that the proposed method achieves excellent performance on all datasets and is significantly better than current methods in terms of noise immunity. In this section, we evaluate the effectiveness of the proposed UGG-Re ID on five commonly used datasets and compare it with some state-of-the-art methods. |
| Researcher Affiliation | Academia | 1Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Artificial Intelligence, Anhui University, Hefei, China 2Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China EMAIL, EMAIL |
| Pseudocode | No | The paper describes the methodology using textual explanations and mathematical formulas, but it does not contain a clearly labeled 'Pseudocode' or 'Algorithm' block. |
| Open Source Code | Yes | Our code is available at https://github.com/wanxixi11/UGG-Re ID. |
| Open Datasets | Yes | UGG-Re ID is comprehensively evaluated on five representative multi-modal object Re ID datasets, encompassing diverse spectral modalities. Experimental results show that the proposed method achieves excellent performance on all datasets and is significantly better than current methods in terms of noise immunity. Our code is available at https://github.com/wanxixi11/UGG-Re ID. |
| Dataset Splits | Yes | Table 7: Details of the datasets partition settings and their corresponding challenges, */* represents ID/Sample. RGBNT201 Train 171/3951 Query 30/836 Gallery 30/836 Market1501-MM Train 751/12936 Query 750/3368 Gallery 751/15913 MSVR310 Train 155/1032 Query 52/591 Gallery 155/1055 RGBNT100 Train 50/8675 Query 50/1715 Gallery 50/8575 WMVEID863 Train 603/10446 Query 210/2904 Gallery 272/3678 |
| Hardware Specification | Yes | All experiments are conducted using Py Torch on a single NVIDIA RTX 4090 GPU. |
| Software Dependencies | No | The paper mentions 'Py Torch' and 'Python' but does not specify their version numbers or any other software dependencies with version numbers. |
| Experiment Setup | Yes | Implementation Details. For all experiments, we set the number of experts at C = 4 and utilize k = 1 for the TOPk selection. The loss terms are weighted with λ1 = 0.1 and λ2, λ3 = 0.0001, respectively. The number of layers for GPGCN L is set to 2. Our code is implemented in Python using the Py Torch framework and will be released publicly upon acceptance. The model is fine-tuned with Adam (learning rate: 0.00035) for 40 epochs. More details of the experiments are provided in the supplementary material. |