Getting to 99% Accuracy in Interactive Segmentation
By Marco Forte, Brian L. Price, Scott D. Cohen, Ning Xu, Franccois Piti'e. 2020
40 citations recorded by the source corpus.
Interactive object cutout tools are the cornerstone of the image editing workflow. Recent deep-learning based interactive segmentation algorithms have made significant progress in handling complex images and rough binary selections can typically be obtained with just a few clicks. Yet, deep learning techniques tend to plateau once this rough selection has been reached. In this work, we interpret this plateau as the inability of current algorithms to sufficiently leverage each user interaction and also as the limitations of current training/testing datasets. We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow. We also show that significant improvements can be further gained by introducing a synthetic training dataset that is specifically designed for complex object boundaries. Comprehensive experiments support our approach, and our network achieves state of the art performance.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jiashi Feng
- Ming-Hsuan Yang
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Alan L. Yuille
- Jitendra Malik
Citations in the corpus
- Segment Anything (2023, methodology): “Following [92, 37], we simulate an interactive setup by randomly sampling prompts in 11 rounds per mask, allowing SAM to integrate seamlessly into our data engine.”
- FocalClick: Towards Practical Interactive Image Segmentation (2022, methodology): “Although [10, 36] concatenate the previous mask with the input image and the click maps, they do not perform well.”
- Deep Interactive Thin Object Selection (2021, methodology): “In order to accommodate the batch size of 1, we follow [10] by replacing all the batch normalization (BN) layers with group normalization (GN) [47] with weight standardization [38].”