A Causal Debiasing Framework for Unsupervised Salient Object Detection

Authors: Xiangru Lin, Ziyi Wu, Guanqi Chen, Guanbin Li, Yizhou Yu1610-1619

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on 6 benchmark datasets show that our method significantly outperforms previous unsupervised state-of-the-art methods and even surpasses some of the supervised methods, demonstrating our debiasing framework s effectiveness.
Researcher Affiliation Collaboration 1Sun Yat-sen University 2The University of Hong Kong 3Deepwise AI Lab
Pseudocode No The paper includes mathematical equations and descriptions of methods but no clearly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code No The paper does not provide any specific links or explicit statements about the availability of open-source code for the described methodology.
Open Datasets Yes to make fair comparisons with previous state-of-the-art method (Nguyen et al. 2019) trained on MSRAB (Liu et al. 2007) dataset... to make fair comparisons with previous state-of-the-art method (Zhang, Xie, and Barnes 2020) trained on DUTS (Wang et al. 2017) dataset
Dataset Splits No The paper mentions 'training set' and 'test set' but does not explicitly specify how the data was split into training, validation, and test sets, nor does it provide details on a dedicated validation set for hyperparameter tuning.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with their version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup Yes α is a blending parameter set to 0.7. ... γ is a temperature parameter set to 1.5. ... β2 is set to 0.3 as in the standard evaluation metric. ... κ is set to 10 as in (Qin et al. 2019; Zhang, Xie, and Barnes 2020; Zhang et al. 2020b). ... T is a temperature parameter set to 1.5.