Domain Generalization via Conditional Invariant Representations

Authors: Ya Li, Mingming Gong, Xinmei Tian, Tongliang Liu, Dacheng Tao

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on both synthetic and real data demonstrate the effectiveness of the proposed method.
Researcher Affiliation Academia CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, China UBTECH Sydney Artificial Intelligence Institute, SIT, FEIT, The University of Sydney, Australia Department of philosophy, Carnegie Mellon University Department of Biomedical Informatics, University of Pittsburgh
Pseudocode Yes Algorithm 1 Conditional invariant domain generalization
Open Source Code No The paper does not provide any links to source code or explicitly state that the code is publicly available.
Open Datasets Yes VLCS is an image classification dataset widely used for evaluating the performance of domain generalization. This dataset contains images from four different sub-datasets corresponding to four domains: PASCAL VOC2007 (V) (Everingham et al. 2010), Label Me (L) (Russell et al. 2008), Caltech-101 (C) (Griffin, Holub, and Perona 2007), and SUN09 (S) (Choi et al. 2010). [...] The Office+Caltech image dataset consists of ten overlapping categories between the Office dataset and the Caltech256 dataset (C).
Dataset Splits Yes All parameters are selected through validation, in which 30% of the training data is selected as validation set.
Hardware Specification No The paper mentions using De CAF and CAFFE networks for feature extraction, but does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper mentions the use of 'De CAF network' and 'CAFFE network' for feature extraction, but does not specify version numbers for these or any other software dependencies.
Experiment Setup Yes The images are preprocessed by subtracting the mean values and cropped on the central 224 224 region out of the 256 256 resized images. Then the preprocessed images are fed into the De CAF network and extracted the 4096 dimensional De CAF6 features (Donahue et al. 2014). We randomly select 70% of the data as training set from each domain and repeat the random selection five times. [...] All parameters are selected through validation, in which 30% of the training data is selected as validation set. All kernel methods use a RBF kernel and the learned features are classified using KNN except for Undo-Bias.