SEVEN: Deep Semi-supervised Verification Networks
Authors: Vahid Noroozi, Lei Zheng, Sara Bahaadini, Sihong Xie, Philip S. Yu
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on four verification tasks demonstrate that SEVEN significantly outperforms other state-of-the-art deep semisupervised techniques when labeled data are in short supply. Furthermore, SEVEN is competitive with fully supervised baselines trained with a larger amount of labeled data. It indicates the importance of the generative component in SEVEN. |
| Researcher Affiliation | Academia | Department of Computer Science, University of Illinois at Chicago, IL, USA Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, USA Computer Science and Engineering Department, Lehigh University, Bethlehem, PA, USA |
| Pseudocode | Yes | Algorithm 1: Training procedure of SEVEN |
| Open Source Code | No | The paper does not provide any explicit link to open-source code or state that the code for their method is publicly available. |
| Open Datasets | Yes | MNIST: It is a dataset of 70000 grayscale images of handwritten digits from 0 to 9. We use the original split of 60000/10000 for the training and test sets. [...] US Postal Service (USPS) [Hull, 1994]: It is a dataset of 9298 handwritten digits automatically scanned from envelopes by the US Postal Service. [...] Labeled Faces in the Wild (LFW) [Huang et al., 2012]: It is a database of face images that contains 1100 positive and 1100 negative pairs in the training set, and 500 positive and 500 negative pairs in the test set. [...] Biosecur ID-SONOF (SONOF) [Galbally et al., 2015]: We use a subset of this dataset comprising signatures collected from 132 users, each user has 16 signatures. |
| Dataset Splits | Yes | MNIST: We use the original split of 60000/10000 for the training and test sets. [...] We selected randomly 85% of the images for the training set. [...] LFW: 1100 positive and 1100 negative pairs in the training set, and 500 positive and 500 negative pairs in the test set. [...] We divided the users randomly into 100/32 for the training and test purposes. [...] All the parameters of SEVEN and also other baselines are selected based on a validation on a randomly selected 20% subset of the training data. |
| Hardware Specification | No | The paper does not explicitly describe the hardware used to run its experiments. |
| Software Dependencies | No | The paper mentions 'RMSProp optimizer' but does not specify any software libraries or frameworks (e.g., TensorFlow, PyTorch) with version numbers that would be necessary for reproduction. |
| Experiment Setup | Yes | The l2-regularization parameter β is selected from {1e 4, 1e 3, 0.01, 0.1} for each dataset separately. The parameter α that controls the trade-off between generative and discriminative objectives is selected from {0.01, 0.05, 0.1, 0.2, 0.5, 1.0, 2.0, 5.0}. It is set to 0.05, 0.1, 0.05, and 0.2 for MNIST, LFW, USPS and SONOF, respectively. Parameter τ is set to 0.5 for all the four datasets. All the neural network models are trained for 150 epochs. The pre-training is also performed for 150 epochs for the baselines which require pre-training. RMSProp optimizer is used for the training of all the neural networks with the default value λ = 0.001 recommended in the original paper. |