DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer

2023 IEEE/CVF International Conference on Computer Vision (ICCV)(2023)

Cited 3|Views56
No score
Abstract
Most state-of-the-art instance segmentation methods rely on large amounts of pixel-precise ground-truth annotations for training, which are expensive to create. Interactive segmentation networks help generate such annotations based on an image and the corresponding user interactions such as clicks. Existing methods for this task can only process a single instance at a time and each user interaction requires a full forward pass through the entire deep network. We introduce a more efficient approach, called DynaMITe, in which we represent user interactions as spatio-temporal queries to a Transformer decoder with a potential to segment multiple object instances in a single iteration. Our architecture also alleviates any need to re-compute image features during refinement, and requires fewer interactions for segmenting multiple instances in a single image when compared to other methods. DynaMITe achieves state-of-the-art results on multiple existing interactive segmentation benchmarks, and also on the new multi-instance benchmark that we propose in this paper.
More
Translated text
Key words
dynamic query bootstrapping,segmentation,multi-object
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined