Rescuing Deep Hashing from Dead Bits Problem
Authors: Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on three datasets demonstrate the efficiency of the proposed gradient amplifier and the error-aware quantization loss. |
| Researcher Affiliation | Academia | 1Institute of Information Engineering, Chinese Academy of Sciences 2School of Cyber Security, University of Chinese Academy of Sciences |
| Pseudocode | Yes | Algorithm 1 The learning algorithm for RDH |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of their proposed method. |
| Open Datasets | Yes | The experiments of RDH are conducted on three widely used datasets: CIFAR-10 [Krizhevsky et al., 2009], MS-COCO [Lin et al., 2014], and NUS-WIDE [Chua et al., 2009]. 1http://www.cs.toronto.edu/ kriz/cifar.html 2https://cocodataset.org/ 3https://lms.comp.nus.edu.sg/wp-content/uploads/2019/research /nuswide/NUS-WIDE.html |
| Dataset Splits | Yes | CIFAR-10 is a single-label dataset, containing 60,000 color images... we randomly sample 1,000 images (100 images per class) as the query set, and the rest are used to form the gallery set. Then we randomly select 5,000 images (500 images per class) from the gallery as the training set. MS-COCO... contains 82,783 training images and 40,504 validation images... NUS-WIDE... we randomly select 2,100 images (100 images per class) as the query set. From the rest images, we randomly choose 10,500 images (500 images per class) to make up the training set. |
| Hardware Specification | Yes | All the experiments are conducted on a single NIVDIA RTX 2080ti GPU. |
| Software Dependencies | No | All of these methods are implemented on Py Torch [Paszke et al., 2019]. The specific version number of PyTorch or any other software dependencies is not mentioned. |
| Experiment Setup | Yes | In RDH, SGD is utilized as the optimizer with 1e 5 weight decay. The initial learning rate is set to 1e 2. Cosine annealing the learning rate scheduler [Loshchilov and Hutter, 2016] is leveraged to gradually reduce learning rate to zero. The batch size is set to 128. We set τ = 0.99. η is set to 1 for CIFAR-10 and 0.1 for the others. |