Adaptive Uncertainty-Based Learning for Text-Based Person Retrieval
Authors: Shenshen Li, Chen He, Xing Xu, Fumin Shen, Yang Yang, Heng Tao Shen
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate that our AUL method consistently achieves state-of-the-art performance on three benchmark datasets in supervised, weakly supervised, and domain generalization settings. |
| Researcher Affiliation | Academia | School of Computer Science and Engineering and Center for Future Media, University of Electronic Science and Technology of China, China |
| Pseudocode | No | The paper describes its method using mathematical formulations and descriptive text, but does not include explicit pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/CFM-MSG/Code-AUL. |
| Open Datasets | Yes | We evaluate our model on three benchmark datasets, including: 1) CUHK-PEDES (Li et al. 2017)... 2) ICFG-PEDES (Ding et al. 2021)... 3) RSTPReid (Zhu et al. 2021)... |
| Dataset Splits | No | The paper explicitly mentions training and test sets for the ICFG-PEDES dataset but does not explicitly detail a separate validation set split or its use. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions PyTorch as the implementation framework but does not provide specific version numbers for it or any other software libraries used. |
| Experiment Setup | Yes | Then we resize the image to 384 128 and set the length for each textual token sequence to 56. Initialed by parameters of the first stage, we trained our AUL model with Py Torch for 35 epochs using the Adam optimizer (Kingma and Ba 2015) with a learning rate initialed by 5e-5 and decayed to 5e-6 following a linear learning rate decay. The batch size is set as 128. Finally, λ and γ0 are set to 0.8 and 1.0 for all experiments. |