Unsupervised Hashing with Contrastive Information Bottleneck
Authors: Zexuan Qiu, Qinliang Su, Zijing Ou, Jianxing Yu, Changyou Chen
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines. |
| Researcher Affiliation | Academia | 1School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China 2School of Artificial Intelligence, Sun Yat-sen University, Guangdong, China 3CSE Department, SUNY at Buffalo |
| Pseudocode | No | The paper describes its methods using mathematical equations and diagrams, but does not include any pseudocode or explicitly labeled algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/qiuzx2/CIBHash. |
| Open Datasets | Yes | 1) CIFAR-10 is a dataset consisting of 60, 000 images from 10 classes [Krizhevsky and Hinton, 2009]. [...] 2) NUS-WIDE is a multi-label dataset containing 269, 648 images from 81 categories [Chua et al., 2009]. [...] 3) MSCOCO is a large-scale dataset for object detection, segmentation and captioning [Lin et al., 2014]. |
| Dataset Splits | No | The paper describes splitting data into training, query, and database sets but does not explicitly mention a separate 'validation' set or split. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments. |
| Software Dependencies | No | The paper mentions 'Py Torch' and 'Adam optimizer' but does not specify their version numbers or any other software dependencies with versions. |
| Experiment Setup | Yes | For images from the three datasets, they are all resized to 224 224 3. [...] the encoder network fθ( ) is constituted by a pretrained VGG-16 network [Simonyan and Zisserman, 2015] followed by an one-layer Re LU feedforward neural network with 1024 hidden units. [...] During the training, following previous works [Su et al., 2018; Shen et al., 2019], we fix the parameters of pre-trained VGG-16 network, while only training the newly added feedfoward neural network. [...] the learning rate is set to be 0.001. The temperature τ is set to 0.3, and β is set to 0.001. |