A survey of recent interactive image segmentation methods

Ramadan, Hiba; Lachqar, Chaymae; Tairi, Hamid

doi:10.1007/s41095-020-0177-5

Cited by 53 publications

(30 citation statements)

References 203 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weakly supervised learning for semantic segmentation employs different levels of supervision, like labeling only few pixels (e.g. interactive methods [7]), grouping images containing common objects (e.g. cosegmentation [8]) or providing only image-level labels [9].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Auto-generated Wires Dataset for Semantic Segmentation with Domain-Independence

Zanella

Caporali

Tadaka

et al. 2021

2021 International Conference on Computer, Control and Robotics (ICCCR)

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

“…cosegmentation [8]) or providing only image-level labels [9]. In interactive segmentation frameworks [7] small portions of target objects are roughly highlighted by human operators through markers, called seeds. These seeds are used for a training stage that will produce some rough labels for all other images.…”

Section: Related Workmentioning

confidence: 99%

Auto-generated Wires Dataset for Semantic Segmentation with Domain-Independence

Zanella

Caporali

Tadaka

et al. 2021

2021 International Conference on Computer, Control and Robotics (ICCCR)

View full text Add to dashboard Cite

show abstract

“…The earliest works in interactive segmentation were based on algorithmic approaches for incorporating human inputs into region [45,50,63] or boundary [39,18] processing pipelines. [43] provides a comprehensive survey of interactive segmentation approaches. More recently deep networks have been used to incorporate user feedback to guide their output predictions at the pixel level.…”

Section: Interactive Segmentationmentioning

confidence: 99%

Probabilistic Attention for Interactive Segmentation

Gabbur,

Bilkhu,

Movellan

2021

Preprint

View full text Add to dashboard Cite

We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference. The proposed approach suggests the use of Expectation Maximization algorithms for on-line adaptation of key and value model parameters. This approach is useful for cases in which external agents, e.g., annotators, provide inference-time information about the correct values of some tokens, e.g, the semantic category of some pixels, and we need for this new information to propagate to other tokens in a principled manner. We illustrate the approach on an interactive semantic segmentation task in which annotators and models collaborate on-line to improve annotation efficiency. Using standard benchmarks, we observe that key adaptation boosts model performance (∼ 10% mIoU) in the low feedback regime and value propagation improves model responsiveness in the high feedback regime. A PyTorch layer implementation of our probabilistic attention model will be made publicly available here: https://github.com/apple/ml-probabilistic-attention.

show abstract

“…In GrabCut [13] and its variants [14]- [17] the user inputs are bounding boxes where these methods may also incorporate additional user inputs to refine the segmentation process. A detailed survey on user-assisted segmentation methods can be found in [18].…”

Section: Introductionmentioning

confidence: 99%

A Baseline Statistical Method For Robust User-Assisted Multiple Segmentation

Afser

2022

Preprint

View full text Add to dashboard Cite

Recently, several image segmentation methods that welcome and leverage different types of user assistance have been developed. In these methods, the user inputs can be provided by drawing bounding boxes over image objects, drawing scribbles or planting seeds that help to differentiate between image boundaries or by interactively refining the missegmented image regions. Due to the variety in the types and the amounts of these inputs, relative assessment of different segmentation methods becomes difficult. As a possible solution, we propose a simple yet effective, statistical segmentation method that can handle and utilize different input types and amounts. The proposed method is based on robust hypothesis testing, specifically the DGL test, and can be implemented with time complexity that is linear in the number of pixels and quadratic in the number of image regions. Therefore, it is suitable to be used as a baseline method for quick benchmarking and assessing the relative performance improvements of different types of user-assisted segmentation algorithms. We provide a mathematical analysis on the operation of the proposed method, discuss its capabilities and limitations, provide design guidelines and present simulations that validate its operation.

show abstract

A survey of recent interactive image segmentation methods

Cited by 53 publications

References 203 publications

Auto-generated Wires Dataset for Semantic Segmentation with Domain-Independence

Auto-generated Wires Dataset for Semantic Segmentation with Domain-Independence

Probabilistic Attention for Interactive Segmentation

A Baseline Statistical Method For Robust User-Assisted Multiple Segmentation

Contact Info

Product

Resources

About