Unified Unsupervised Salient Object Detection via Knowledge Transfer

Authors: Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method.
Researcher Affiliation Academia Nanjing University of Aeronautics and Astronautics {ayews233, wutaoliu, pan.gao, daiqun}@nuaa.edu.cn, qinjiebuaa@gmail.com
Pseudocode No The paper describes its methods verbally and with mathematical formulations but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes Code and supplement materials are available at https://github.com/I2-Multimedia-Lab/A2S-v3.
Open Datasets Yes RGB SOD: We use the training subsets of DUTS [Wang et al., 2017] to train our method. RGB-D SOD: We choose 2185 samples from the training subsets of NLPR [Peng et al., 2014] and NJUD [Ju et al., 2014] as the training set. RGB-T SOD: 2500 images in VT5000 [Tu et al., 2022a] are for training. Video SOD: We choose the training splits of DAVIS [Perazzi et al., 2016] and DAVSOD [Fan et al., 2019] to train our method. Remote Sensing Image SOD: We choose the training splits of ORSSD [Li et al., 2019] and EORSSD [Zhang et al., 2020b] to train our method.
Dataset Splits No The paper lists datasets used for training and testing/evaluation but does not specify explicit percentages or counts for training, validation, and test splits needed for reproduction. It refers to 'training subsets' and 'testing subsets' of standard datasets, but does not detail how a validation set, if any, was derived or used for hyperparameter tuning in a reproducible manner.
Hardware Specification Yes All experiments were implemented on a single RTX 3090 GPU.
Software Dependencies No The paper does not provide specific version numbers for any software dependencies or libraries used (e.g., Python, PyTorch, or other frameworks/libraries).
Experiment Setup Yes The batch size is set to 8 and input images are resized to 320 320. Horizontal flipping is employed as our data augmentation. We train the saliency cue extractor for 20 epochs using the SGD optimizer with an initial learning rate of 0.1, which is decayed linearly. We train the saliency detector for 10 epochs using the SGD optimizer with a learning rate of 0.005.