Adversarial-Learned Loss for Domain Adaptation
Authors: Minghao Chen, Shuai Zhao, Haifeng Liu, Deng Cai3521-3528
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our ALDA outperforms state-of-the-art approaches in four standard domain adaptation datasets. Our code is available at https://github.com/ZJULearning/ALDA. |
| Researcher Affiliation | Collaboration | State Key Lab of CAD&CG, College of Computer Science, Zhejiang University, Hangzhou, China Fabu Inc., Hangzhou, China Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China |
| Pseudocode | No | The paper describes the method using mathematical formulations and diagrams, but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/ZJULearning/ALDA. |
| Open Datasets | Yes | Digits. Following the evaluation protocol of (Long et al. 2017a), we experiment on three adaptation scenarios: USPS to MNIST (U M), MNIST to USPS (M U), and SVHN to MNIST (S M). MNIST (Le Cun 1998) contains 60, 000 images of handwritten digits and USPS (Hull 1994) contains 7, 291 images. Street View House Numbers (SVHN) (Netzer et al. 2011) consists of 73, 257 images with digits and numbers in natural scenes. We report the evaluation results on the test sets of MNIST and USPS. Office-31 (Saenko and Kulis 2010) is a commonly used dataset for unsupervised domain adaptation, which contains 4, 652 images and 13 categories collected from three domains: Amazon (A), Webcam (W) and DSLR (D). Office-Home (Venkateswara et al. 2017) is a more difficult domain adaptation dataset than office-31, including 15, 500 images from four different domains: Artistic images (Ar), Clip Art (Cl), Product images (Pr) and Real-World (Rw). Vis DA-2017 (Peng et al. 2017) is a large-scale dataset and challenge for unsupervised domain adaptation from simulation to real. |
| Dataset Splits | No | The paper mentions using training and test sets, and evaluates on the validation set of Vis DA, but it does not provide specific details on how these splits are generated (e.g., percentages, counts, or splitting methodology) to ensure reproducibility beyond referencing standard datasets which might have predefined splits implicitly. |
| Hardware Specification | No | The paper does not provide specific details on the hardware used to run the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | We implement the algorithms using Py Torch (Paszke et al. 2017). (PyTorch is mentioned but no version). |
| Experiment Setup | Yes | For digits datasets, we adopt the generator and classifier networks used in (French, Mackiewicz, and Fisher 2018) and optimize the model using Adam (Kingma and Ba 2015) gradient descent with learning rate 1 × 10−3. ... For the other three datasets, we employ Res Net-50 (He et al. 2016) as the generator network. The Res Net-50 is pretrained on Image Net (Deng et al. 2009). Our discriminator consists of three fully connected layers with dropout, which is the same as other works (Ganin et al. 2016; Long et al. 2017a). As we train the classifier and discriminator from scratch, we set their learning rates to be 10 times that of the generator. We train the model with Stochastic Gradient Descent (SGD) optimizer with the momentum of 0.9. We schedule the learning rate with the strategy in (Ganin et al. 2016): the learning rate is adjusted by ηp = η0 (1+αq)β , where q is the training progress linearly changing from 0 to 1, η0 = 0.01, α = 10, β = 0.75. We implement the algorithms using Py Torch (Paszke et al. 2017). There are two hyper-parameters in our method: the threshold δ of pseudo-labels and the trade-off λ. ... We set δ to 0.6 for digit adaptation and 0.9 for office-31, office-home datasets and Vis DA dataset. In all experiment, λ is gradually increased from 0 to 1 by 2/(1+exp(−10q)−1), same as (Long et al. 2017a). |