Attention-guided Contrastive Hashing for Long-tailed Image Retrieval

Authors: Xuan Kou, Chenghao Xu, Xu Yang, Cheng Deng

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on two popular benchmarks verify the superiority of the proposed method.
Researcher Affiliation Academia Xuan Kou , Chenghao Xu , Xu Yang and Cheng Deng Xidian University {kouxuan98, shydyl1456113691, xuyang.xd, chdeng.xd}@gmail.com
Pseudocode Yes Algorithm 1 Training algorithm of ACHNet
Open Source Code Yes Our code is available at: https://github.com/KUXN98/ACHNet.
Open Datasets Yes Cifar-100 is a dataset widely used in the field of image classification and retrieval. It contains 60000 images at 32 32 from 10 categories. We use 50000 images as the database, with an average of 500 images per category, and the remaining 10000 images as the query set, with 100 images per category. Then we follow Zipf s law to randomly sample the training set from database, building three unbalanced benchmarks according to IF=1, IF=50, and IF=100. Image Net-100... we select 100 categories... The database has 13000 images... query set has 5000 images..., the training set is randomly selected from the database.
Dataset Splits Yes We use 50000 images as the database, with an average of 500 images per category, and the remaining 10000 images as the query set, with 100 images per category. Then we follow Zipf s law to randomly sample the training set from database, building three unbalanced benchmarks according to IF=1, IF=50, and IF=100. ... The database has 13000 images in total and 1300 images in each category, while query set has 5000 images in total and 50 images in each category , the training set is randomly selected from the database.
Hardware Specification No The paper does not specify the exact hardware (e.g., GPU models, CPU types) used for the experiments.
Software Dependencies No The paper mentions using 'resnet34' and 'RMSprop algorithm' but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes On the Cifar-100, we set the learning rate as 1e-5. On the Image Net, we set the learning rate of the feature extractor as 1e-6 and the rest as 1e-4, the weight decay is 5e-4. we adopt the cosine annealing strategy to adjust the learning rate within each epoch, the final learning rate will be 0.01 times the initial value. Other hyperparametric are set as follows: batch size=8, β=0.2 for Cifar-100 and β=0.8 for Image Net-100, the total number of epochs is 100.