Inference Time on Saliency Prediction SOTA comparison (test)
0.02Inference Time (s)DINet
Evaluation results
| Method | Links | |
|---|---|---|
| DINetBackbone network=Dilated ResNet50, #parameters=27.04M, key module=Dilated inception module for multi-scale, Input image size=240 x 3202019.04 | 0.02 | |
| DVABackbone network=VGG16, #parameters=25.07M, key module=Skip-layers for multi-scale, Input image size=224 x 2242019.04 | 0.02 | |
| DINetBackbone network=Dilated ResNet50, #parameters=27.04M, key module=Dilated inception module for multi-scale, Input image size=320 x 4802019.04 | 0.03 | |
| DINetBackbone network=Dilated ResNet50, #parameters=27.04M, key module=Dilated inception module for multi-scale, Input image size=480 x 6402019.04 | 0.06 | |
| SAMBackbone network=Dilated VGG16, #parameters=51.84M, key module=Conv-LSTMs [56] for iterative refinement, Input image size=240 x 3202019.04 | 0.07 | |
| SAMBackbone network=Dilated ResNet50, #parameters=70.09M, key module=Conv-LSTMs [56] for iterative refinement, Input image size=240 x 3202019.04 | 0.09 | |
| DSCLRCNBackbone network=Dilated ResNet50 + Places-CNN, #parameters=>33.71M, key module=Spatial LSTMs [57] for context incorporation, Input image size=480 x 640 + 227 x 2272019.04 | 0.27 |