SALOD

November 28, 2025 ยท View on GitHub

Here is the SALient Object Detection (SALOD) benchmark (paper link), 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). Some other networks are debugging now, it is welcome for your contributions on these models.

Our new unsupervised A2S-v2 method was accepted by CVPR 2023!

You can contact me through the official email: csehjzhou@ust.hk

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.
Original SOD datasets from: SOD, including DUTS-TR,DUTS-TE,ECSSD,SOD,PASCAL-S,HKU-IS,DUT-OMRON.
COD datasets from: COD, 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 [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.GMACsFPSmax-Fave-FFbwMAESMem
DHSNet24.213.849.2.909.871.863.037.905.925
Amulet79.81093.835.1.897.856.846.042.896.919
NLDF41.1115.130.5.908.868.859.038.903.930
SRM61.220.234.3.893.851.841.042.892.925
DSS134.335.327.3.906.868.859.038.901.933
PiCaNet106.136.914.8.900.864.852.043.896.924
BASNet95.547.232.8.911.872.863.040.905.925
CPD47.914.722.7.913.884.874.034.911.938
PoolNet68.366.933.9.916.882.875.035.911.938
EGNet111.7222.810.2.913.884.875.036.908.936
SCRN25.212.519.3.916.881.872.035.910.935
F3Net25.513.639.2.911.878.869.036.908.932
GCPA67.154.337.8.914.884.874.036.910.937
ITSD25.719.629.4.918.880.873.037.910.932
MINet162.48723.5.912.874.866.038.908.931
LDF25.212.837.5.913.879.873.035.909.938
GateNet128.69625.9.912.882.870.037.906.934
PFSNet31.237.521.7.912.879.865.038.904.931
CTDNet24.610.264.2.918.887.880.033.913.940
EDN35.116.127.4.916.883.875.036.910.934

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(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:

MethodsPublish.PaperSrc Code
MENetCVPR 2023openaccessPyTorch
EDNTIP 2022TIPPytorch
CTDNetACM MM 2021ACMPytorch
PFSNetAAAI 2021AAAI.orgPytorch
GateNetECCV 2020springerPytorch
LDFCVPR 2020openaccessPytorch
MINetCVPR 2020openaccessPytorch
ITSDCVPR 2020openaccessPytorch
GCPAAAAI 2020aaai.orgPytorch
F3NetAAAI 2020aaai.orgPytorch
SCRNICCV 2019openaccessPytorch
EGNetICCV 2019openaccessPytorch
PoolNetCVPR 2019openaccessPytorch
CPDCVPR 2019openaccessPytorch
BASNetCVPR 2019openaccessPytorch
DSSTPAMI 2019IEEE/ArXivPytorch
PicaNetCVPR 2018openaccessPytorch
SRMICCV 2017openaccessPytorch
AmuletICCV 2017openaccessPytorch
NLDFCVPR 2017openaccessPytorch/TF
DHSNetCVPR 2016openaccessPytorch
Tuning---------------
*PAGECVPR2019openaccessTF
*PFACVPR2019openaccessPytorch
*PFPNAAAI2020aaai.orgPytorch

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

@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}
}