SINetV2 | 0.791 | 274 | 0.094 | 0.727 | 0.644 | 0.558 | Concealed Object Detection | |
PFNet | 0.786 | 253 | 0.094 | 0.722 | 0.646 | 0.552 | Camouflaged Object Segmentation with Distraction Mining | |
STDC | 0.798 | 249 | 0.090 | 0.723 | 0.648 | 0.562 | Rethinking BiSeNet For Real-time Semantic Segmentation | |
DeeplabV3+ | 0.772 | 234 | 0.102 | 0.694 | 0.601 | 0.506 | Rethinking Atrous Convolution for Semantic Image Segmentation | |
MBV3 | 0.818 | 274 | 0.083 | 0.740 | 0.669 | 0.595 | Searching for MobileNetV3 | |
InSPyReNet (HR scale) | 0.894 | 110 | 0.045 | 0.873 | 0.845 | 0.788 | Revisiting Image Pyramid Structure for High Resolution Salient Object Detection | |
PSPNet | 0.791 | 267 | 0.089 | 0.725 | 0.645 | 0.557 | Pyramid Scene Parsing Network | |
IS-Net | 0.820 | 149 | 0.074 | 0.787 | 0.740 | 0.662 | Highly Accurate Dichotomous Image Segmentation | |