Learning Token-Based Representation for Image Retrieval

Authors: Hui Wu, Min Wang, Wengang Zhou, Yang Hu, Houqiang Li2703-2711

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted to evaluate our approach, which outperforms the state-of-the-art methods on the Revisited Oxford and Paris datasets.
Researcher Affiliation Academia 1 CAS Key Laboratory of GIPAS, University of Science and Technology of China 2 Institute of Artificial Intelligence, Hefei Comprehensive National Science Center wh241300@mail.ustc.edu.cn, wangmin@iai.ustc.edu.cn, {zhwg, eeyhu, lihq}@ustc.edu.cn
Pseudocode No The paper describes its method using text and mathematical equations, and includes a block diagram (Figure 2), but no pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository.
Open Datasets Yes The clean version of Google landmarks dataset V2 (GLDv2-clean) (Weyand et al. 2020) is used for training.
Dataset Splits Yes We randomly divide it into two subsets train / val with 80%/20% split. The train split is used for training model, and the val split is used for validation.
Hardware Specification Yes We use a batch size of 128 to train our model on 4 NVIDIA RTX 3090 GPUs for 30 epochs... on a single thread GPU (RTX 3090) / CPU (Intel Xeon CPU E5-2640 v4 @ 2.40GHz).
Software Dependencies No The paper mentions using SGD 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 use a batch size of 128 to train our model on 4 NVIDIA RTX 3090 GPUs for 30 epochs... SGD is used to optimize the model, with an initial learning rate of 0.01, a weight decay of 0.0001, and a momentum of 0.9. ... The dimension d of the global feature is set as 1024. For the Arc Face margin loss, we empirically set the margin m as 0.2 and the scale γ as 32.0. Refinement block number N is set to 2.