f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

CVPR 2020 Konstantin SofiiukIlia PetrovOlga BarinovaAnton Konushin

Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown objects it cannot achieve satisfactory result even with a large amount of user input... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Interactive Segmentation Berkeley f-BRS-B (ResNet-50) [email protected] 4.34 # 1
Interactive Segmentation DAVIS f-BRS-B (ResNet-101) [email protected] 5.04 # 1
[email protected] 7.41 # 1
Interactive Segmentation GrabCut f-BRS-B (ResNet-34) [email protected] 2 # 1
[email protected] 2.46 # 1
Interactive Segmentation SBD f-BRS-B (ResNet-101) [email protected] 4.81 # 1
[email protected] 7.73 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet