Consensus Adversarial Domain Adaptation
Authors: Han Zou, Yuxun Zhou, Jianfei Yang, Huihan Liu, Hari Prasanna Das, Costas J. Spanos5997-6004
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments are conducted on the task of digit recognition across multiple benchmark datasets and a real-world problem involving Wi Fi-enabled device-free gesture recognition under spatial dynamics. The results show the compelling performance of CADA versus the state-of-the-art unsupervised domain adaptation (UDA) and supervised domain adaptation (SDA) methods. |
| Researcher Affiliation | Academia | 1Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA 2School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore {hanzou, yxzhou, liuhh, hpdas, spanos}@berkeley.edu, yang0478@ntu.edu.sg |
| Pseudocode | No | The paper describes the steps of the CADA and F-CADA frameworks sequentially in text and through block diagrams (Figure 1 and 2), but does not include any formal pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain an explicit statement about the release of source code for the proposed methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | 3 public digit datasets, MNIST (Le Cun et al. 1998), USPS (Hull 1994), and SVHN (Netzer et al. 2011), which consist 10 classes of digits are used in our digit adaptation experiments. |
| Dataset Splits | No | The models are trained using the full training sets and evaluated on the full testing sets. |
| Hardware Specification | Yes | We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies or libraries used in the experiments. |
| Experiment Setup | No | We repeat the experiment 50 times for each digit adaptation case and performed model selection based on the recent Bayesian optimization technique (Malkomes, Schaff, and Garnett 2016) to identify optimal choices of all hyper-perimeters, e.g., the structure and dropout rate of the encoder, the decay fact of F-CADA, etc. |