Distant Domain Transfer Learning

Authors: Ben Tan, Yu Zhang, Sinno Pan, Qiang Yang

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical studies on image classification problems demonstrate the effectiveness of the proposed algorithm, and on some tasks the improvement in terms of the classification accuracy is up to 17% over non-transfer methods. ... In this section, we conduct empirical studies to evaluate the proposed SLA algorithm from three aspects.
Researcher Affiliation Academia Hong Kong University of Science and Technology, Hong Kong **Nanyang Technological University, Singapore
Pseudocode Yes Algorithm 1 The Selective Learning Algorithm (SLA)
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes The datasets used for experiments include Caltech-256 (Griffin, Holub, and Perona 2007) and Animals with Attributes (Aw A)3. ... 3http://attributes.kyb.tuebingen.mpg.de/
Dataset Splits No The paper states 'for each target domain, we randomly sample 6 labeled instances for training, and use the rest for testing' but does not specify a separate validation split or explicit methodology for validation data.
Hardware Specification No The paper mentions deep learning models and CNNs but does not provide any specific details about the hardware (e.g., GPU, CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions software components like SVM, CNN, DTL, STL, and specific kernel and layer types but does not provide any version numbers for programming languages, libraries, or other software dependencies.
Experiment Setup Yes For SVM, we use the linear kernel. For CNN, we implement a network that is composed of two convolutional layers with kernel size 3 3, where each convolutional layer is followed by a max pooling layer with kernel size 2 2, a fully connected layer, and a logistic regression layer. ... Each configuration is repeated 10 times.