# SALOD **Repository Path**: lulululala/SALOD ## Basic Information - **Project Name**: SALOD - **Description**: No description available - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-02-10 - **Last Updated**: 2025-02-10 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # SALOD Here is the SALient Object Detection (SALOD) benchmark ([paper link](https://www.sciencedirect.com/science/article/pii/S0031320323006490)), published in Pattern Recognition. We have re-implemented over 20 SOD methods using the same settings, including input size, data loader and evaluation metrics (thanks to [Metrics](https://github.com/lartpang/Py-SOD-VOS-EvalToolkit)). Some other networks are debugging now, it is welcome for your contributions on these models. *Our new unsupervised [A2S-v2](https://github.com/moothes/A2S-v2) method was accepted by CVPR 2023!* You can contact me through the official email: zhouhj26@mail2.sysu.edu.cn # Latest Update - 2023/06/27: * MENet (CVPR 2023) is available, but not guaranted to achiveve SOTA performance. You may need to setup its loss function and training strategy. * New loss_factory formatting style. See base/loss.py for details. # Datasets Our SALOD dataset can be downloaded from: [SALOD](https://drive.google.com/file/d/1kxhUoWUAnFhOE_ZoA1www8msG2pKHg3_/view?usp=sharing). Original SOD datasets from: [SOD](https://drive.google.com/file/d/17X4SiSVuBmqkvQJe_ScVARKPM_vgvCOi/view?usp=sharing), including DUTS-TR,DUTS-TE,ECSSD,SOD,PASCAL-S,HKU-IS,DUT-OMRON. COD datasets from: [COD](https://drive.google.com/file/d/1zUgaGxr9PeDcfLfBisV2q8QXL6Tp1QzC/view?usp=sharing), including COD-TR (COD-TR + CAMO-TR), COD-TE, CAMO-TE, NC4K. # Results All models are trained with the following setting: 1. ```--strategy=sche_f3net``` for the latest training strategy as original F3Net, LDF, PFSNet and CTDNet; 2. ```--multi``` for multi-scale training; 3. ```--data_aug``` for random croping; 4. 1 * BCE_loss + 1 * IOU_loss as loss. ## Benchmarking results Following the above settings, we list the benchmark results here. All weights can be downloaded from [Baidu disk](https://pan.baidu.com/s/1KXFU09nBElHqP9ffdHWtNw) [pqn6]. **Noted that FPS is tested on our device with batch_size=1, you should test all methods and report the scores on your own device.** Methods | #Para. | GMACs | FPS | max-F | ave-F | Fbw | MAE | SM | em ---- | --- | ----- | ---- | ----- | ----- | ---- | ---- | ---- | ----- DHSNet | 24.2 | 13.8 | 49.2 | .909 | .871 | .863 | .037 | .905 | .925 Amulet | 79.8 | 1093.8 | 35.1 | .897 | .856 | .846 | .042 | .896 | .919 NLDF | 41.1 | 115.1 | 30.5 | .908 | .868 | .859 | .038 | .903 | .930 SRM | 61.2 | 20.2 | 34.3 | .893 | .851 | .841 | .042 | .892 | .925 DSS | 134.3 | 35.3 | 27.3 | .906 | .868 | .859 | .038 | .901 | .933 PiCaNet | 106.1 | 36.9 | 14.8 | .900 | .864 | .852 | .043 | .896 | .924 BASNet | 95.5 | 47.2 | 32.8 | .911 | .872 | .863 | .040 | .905 | .925 CPD | 47.9 | 14.7 | 22.7 | .913 | .884 | .874 | .034 | .911 | .938 PoolNet | 68.3 | 66.9 | 33.9 | .916 | .882 | .875 | .035 | .911 | .938 EGNet | 111.7 | 222.8 | 10.2 | .913 | .884 | .875 | .036 | .908 | .936 SCRN | 25.2 | 12.5 | 19.3 | .916 | .881 | .872 | .035 | .910 | .935 F3Net | 25.5 | 13.6 | 39.2 | .911 | .878 | .869 | .036 | .908 | .932 GCPA | 67.1 | 54.3 | 37.8 | .914 | .884 | .874 | .036 | .910 | .937 ITSD | 25.7 | 19.6 | 29.4 | .918 | .880 | .873 | .037 | .910 | .932 MINet | 162.4 | 87 | 23.5 | .912 | .874 | .866 | .038 | .908 | .931 LDF | 25.2 | 12.8 | 37.5 | .913 | .879 | .873 | .035 | .909 | .938 GateNet | 128.6 | 96 | 25.9 | .912 | .882 | .870 | .037 | .906 | .934 PFSNet | 31.2 | 37.5 | 21.7 | .912 | .879 | .865 | .038 | .904 | .931 CTDNet | 24.6 | 10.2 | 64.2 | .918 | .887 | .880 | .033 | .913 | .940 EDN | 35.1 | 16.1 | 27.4 | .916 | .883 | .875 | .036 | .910 | .934 ## Conventional SOD results The orig. means the results of official saliency predictions, while ours are the re-implemented results in our benchmark. The weights of these models can be downloaded from: [Baidu Disk](https://pan.baidu.com/s/1ByHuao32_2fUSXV7nNNMIA)(cs6u)
Method Src PASCAL-S ECSSD HKU-IS DUTS-TE DUT-OMRON
max-FMAE max-FMAE max-FMAE max-FMAE max-FMAE
DHSNet orig. .820.091 .906.059 .890.053 .808.067 ----
ours .870.063 .944.036 .935.031 .887.040 .805.062
Amulet orig. .828.100 .915.059 .897.051 .778.085 .743.098
ours .871.066 .936.045 .928.036 .871.044 .791.065
NLDF orig. .822.098 .905.063 .902.048 .813.065 .753.080
ours .872.064 .937.042 .927.035 .882.044 .796.068
SRM orig. .838.084 .917.054 .906.046 .826.059 .769.069
ours .854.069 .922.046 .904.043 .846.049 .774.068
DSS orig. .831.093 .921.052 .900.050 .826.065 .769.063
ours .870.063 .937.039 .924.035 .878.040 .800.059
PiCANet orig. .857.076 .935.046 .918.043 .860.051 .803.065
ours .867.074 .938.044 .927.036 .879.046 .798.077
BASNet orig. .854.076 .942.037 .928.032 .859.048 .805.056
ours .884.057 .950.034 .943.028 .907.033 .833.052
CPD orig. .859.071 .939.037 .925.034 .865.043 .797.056
ours .883.057 .946.034 .934.031 .892.037 .815.059
PoolNet orig. .863.075 .944.039 .931.034 .880.040 .808.056
ours .877.062 .946.035 .936.030 .895.037 .812.063
EGNet orig. .865.074 .947.037 .934.032 .889.039 .815.053
ours .880.060 .948.032 .937.030 .892.037 .812.058
SCRN orig. .877.063 .950.037 .934.034 .888.040 .811.056
ours .871.063 .947.037 .934.032 .895.039 .813.063
F3Net orig. .872.061 .945.033 .937.028 .891.035 .813.053
ours .884.057 .950.033 .937.030 .903.034 .819.053
GCPA orig. .869.062 .948.035 .938.031 .888.038 .812.056
ours .885.056 .951.031 .941.028 .905.034 .820.055
ITSD orig. .872.065 .946.035 .935.030 .885.040 .821.059
ours .880.067 .950.036 .939.030 .895.040 .817.072
MINet orig. .867.064 .947.033 .935.029 .884.037 .810.056
ours .874.064 .947.036 .937.031 .893.039 .816.061
LDF orig. .874.060 .950.034 .939.028 .898.034 .820.052
ours .883.058 .951.032 .940.029 .903.035 .818.058
GateNet orig. .869.067 .945.040 .933.033 .888.040 .818.055
ours .867.066 .944.037 .934.031 .891.039 .803.062
PFSNet orig. .875.063 .952.031 .943.026 .896.036 .823.055
ours .883.060 .950.034 .939.030 .899.037 .816.063
CTDNet orig. .878.061 .950.032 .941.027 .897.034 .826.052
ours .885.057 .950.031 .940.028 .904.033 .821.055
EDN orig. .880.062 .951.032 .941.026 .895.035 .828.049
ours .891.058 .953.031 .945.027 .910.032 .837.055
# Available Methods: Methods | Publish. | Paper | Src Code ---- | ----- | ----- | ------ MENet | CVPR 2023 | [openaccess](https://openaccess.thecvf.com/content/CVPR2023/html/Wang_Pixels_Regions_and_Objects_Multiple_Enhancement_for_Salient_Object_Detection_CVPR_2023_paper.html) | [PyTorch](https://github.com/yiwangtz/MENet) EDN | TIP 2022 | [TIP](https://ieeexplore.ieee.org/abstract/document/9756227/)| [Pytorch](https://github.com/yuhuan-wu/EDN) CTDNet | ACM MM 2021 | [ACM](https://dl.acm.org/doi/abs/10.1145/3474085.3475494?casa_token=eKn8q7l2hJEAAAAA%3A4YGBXBpC6cCcFdpekxbaZncgBEru_mi69kNixfZSPeFRhD2gkeKpXIZyuiIW1bH80IuNV9ANmBw)| [Pytorch](https://github.com/zhaozhirui/CTDNet) PFSNet | AAAI 2021 | [AAAI.org](https://ojs.aaai.org/index.php/AAAI/article/view/16331)| [Pytorch](https://github.com/iCVTEAM/PFSNet) GateNet | ECCV 2020 | [springer](https://link.springer.com/chapter/10.1007/978-3-030-58536-5_3)| [Pytorch](https://github.com/Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency) LDF | CVPR 2020 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2020/html/Wei_Label_Decoupling_Framework_for_Salient_Object_Detection_CVPR_2020_paper.html)| [Pytorch](https://github.com/weijun88/LDF) MINet | CVPR 2020 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2020/papers/Pang_Multi-Scale_Interactive_Network_for_Salient_Object_Detection_CVPR_2020_paper.pdf) | [Pytorch](https://github.com/lartpang/MINet) ITSD | CVPR 2020 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2020/papers/Zhou_Interactive_Two-Stream_Decoder_for_Accurate_and_Fast_Saliency_Detection_CVPR_2020_paper.pdf) | [Pytorch](https://github.com/moothes/ITSD-pytorch) GCPA | AAAI 2020 | [aaai.org](https://aaai.org/ojs/index.php/AAAI/article/view/6633) | [Pytorch](https://github.com/JosephChenHub/GCPANet) F3Net | AAAI 2020 | [aaai.org](https://aaai.org/ojs/index.php/AAAI/article/view/6916) | [Pytorch](https://github.com/weijun88/F3Net) SCRN | ICCV 2019 | [openaccess](https://openaccess.thecvf.com/content_ICCV_2019/papers/Wu_Stacked_Cross_Refinement_Network_for_Edge-Aware_Salient_Object_Detection_ICCV_2019_paper.pdf) | [Pytorch](https://github.com/wuzhe71/SCRN) EGNet | ICCV 2019 | [openaccess](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhao_EGNet_Edge_Guidance_Network_for_Salient_Object_Detection_ICCV_2019_paper.pdf) | [Pytorch](https://github.com/JXingZhao/EGNet) PoolNet | CVPR 2019 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_A_Simple_Pooling-Based_Design_for_Real-Time_Salient_Object_Detection_CVPR_2019_paper.pdf) | [Pytorch](https://github.com/backseason/PoolNet) CPD | CVPR 2019 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_Cascaded_Partial_Decoder_for_Fast_and_Accurate_Salient_Object_Detection_CVPR_2019_paper.pdf) | [Pytorch](https://github.com/wuzhe71/CPD) BASNet | CVPR 2019 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2019/papers/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.pdf) | [Pytorch](https://github.com/NathanUA/BASNet) DSS | TPAMI 2019| [IEEE](https://ieeexplore.ieee.org/document/8315520/)/[ArXiv](https://arxiv.org/abs/1611.04849) | [Pytorch](https://github.com/AceCoooool/DSS-pytorch) PicaNet | CVPR 2018 | [openaccess](https://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_PiCANet_Learning_Pixel-Wise_CVPR_2018_paper.pdf) | [Pytorch](https://github.com/Ugness/PiCANet-Implementation) SRM | ICCV 2017 | [openaccess](https://openaccess.thecvf.com/content_ICCV_2017/papers/Wang_A_Stagewise_Refinement_ICCV_2017_paper.pdf) | [Pytorch](https://github.com/xsxszab/SRM-Pytorch) Amulet | ICCV 2017 | [openaccess](https://openaccess.thecvf.com/content_ICCV_2017/papers/Zhang_Amulet_Aggregating_Multi-Level_ICCV_2017_paper.pdf) | [Pytorch](https://github.com/xsxszab/Amulet-Pytorch) NLDF | CVPR 2017 | [openaccess](https://openaccess.thecvf.com/content_cvpr_2017/papers/Luo_Non-Local_Deep_Features_CVPR_2017_paper.pdf) | [Pytorch](https://github.com/AceCoooool/NLDF-pytorch)/[TF](https://github.com/zhimingluo/NLDF) DHSNet | CVPR 2016 | [openaccess](https://openaccess.thecvf.com/content_cvpr_2016/papers/Liu_DHSNet_Deep_Hierarchical_CVPR_2016_paper.pdf) | [Pytorch](https://github.com/xsxszab/DHSNet-Pytorch) `Tuning` | ----- | ----- | ----- *PAGE | CVPR2019 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Salient_Object_Detection_With_Pyramid_Attention_and_Salient_Edges_CVPR_2019_paper.pdf) | [TF](https://github.com/wenguanwang/PAGE-Net) *PFA | CVPR2019 | [openaccess](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Pyramid_Feature_Attention_Network_for_Saliency_Detection_CVPR_2019_paper.pdf) | [Pytorch](https://github.com/dizaiyoufang/pytorch_PFAN) *PFPN | AAAI2020 | [aaai.org](https://ojs.aaai.org/index.php/AAAI/article/view/6892) | [Pytorch](https://github.com/chenquan-cq/PFPN) # Usage ``` # model_name: lower-cased method name. E.g. poolnet, egnet, gcpa, dhsnet or minet. python3 train.py model_name --gpus=0 --trset=[DUTS-TR,SALOD,COD-TR] python3 test.py model_name --gpus=0 --weight=path_to_weight [--save] python3 test_fps.py model_name --gpus=0 # To evaluate generated maps: python3 eval.py --pre_path=path_to_maps ``` # Loss Factory We supply a **Loss Factory** for an easier way to tune the loss functions. loss are defined by ```--loss=loss1,loss2,loss3```, where each loss is formated as ```name_type#weight```. 'name' is one of keys in loss_dict, 'type' usually is one of ('sal', 'edge'), 'weight' is a float number. Here are some examples: ``` python train.py basnet --loss=bce_sal,dice # For saliency prediction # loss = 1 * bce_loss + 1 * dice_loss python train.py basnet --loss=bce_sal#0.3,ssim_sal#0.7 # For saliency prediction # loss = 0.3 * bce_loss + 0.7 * ssim_loss python train.py basnet --loss=bce#0.3,ssim#0.1,iou#0.5,bce_edge#0.2 # For saliency prediction # loss = 0.3 * bce_loss + 0.1 * ssim_loss + 0.5 * iou_loss # For edge prediction # loss = 0.2 * bce_loss ``` # Update Log 2023/06/27: * MENet (CVPR 2023) is available, but need more time for achiveving SOTA performance. 2023/03/17: * Re-organize the structure of our code. 2022/12/07: * Update conventional SOD results and weights. 2022/10/17: * Use ```timm``` library for more backbones. * Code update. * Benchmark results update. 2022/08/09: * Remove loss.py for each method. The loss functions are defined in config.py now. * Weights are uploaded to Baidu Disk. 2022/06/14: * New model: EDN (TIP 2022). 2022/05/25: * In the previous versions, we found that images with large salient regions get 0 ave-F scores, and thus we obtain lower ave-F scores than their original paper. Now, we fix this bug by adding a round function before evaluating. 2022/05/15: * New models: F3Net (AAAI 2020), LDF (CVPR 2020), GateNet (ECCV 2020), PFSNet (AAAI 20221), CTDNet (ACM MM 2021). More models for SOD and COD tasks are coming soon. * New dataset: training on COD task is available now. * Training strategy update. We notice that training strategy is very important for achieving SOTA performance. A new strategy factory is added to /base/strategy.py. Thanks for citing our work ```xml @article{zhou2024benchmarking, title={Benchmarking deep models on salient object detection}, author={Zhou, Huajun and Lin, Yang and Yang, Lingxiao and Lai, Jianhuang and Xie, Xiaohua}, journal={Pattern Recognition}, volume={145}, pages={109951}, year={2024}, publisher={Elsevier} } ```