Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings

@article{Wolny2021SparseOS,
  title={Sparse Object-level Supervision for Instance Segmentation with Pixel Embeddings},
  author={Adrian Wolny and Qin Yu and Constantin Pape and Anna Kreshuk},
  journal={2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={4392-4401}
}
  • A. WolnyQin Yu A. Kreshuk
  • Published 26 March 2021
  • Computer Science
  • 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for annotation and no large public data collections are available for pre-training. We propose to address the dense annotation bottleneck by introducing a proposal-free segmentation approach based on non-spatial embeddings, which exploits the structure of the learned… 

BioSegment: Active Learning segmentation for 3D electron microscopy imaging

This work presents BioSegment, a turnkey platform for experts to automatically process their imaging data and tune segmentation models, which provides a user-friendly annotation ex-perience, integration with familiar microscopy annotation software and a job queue for remote GPU acceleration.

Recurrent Dynamic Embedding for Video Object Segmentation Supplementary Material

We summarize the EMA based methods first select proposal embeddings and then merge the proposal embeddings with the old memory bank in an EMA way. As shown in Eq. 1 (note Eq. 1 is the process to

A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture

The objective of this paper is to familiarize CV researchers with agricultural applications and agricultural practitioners with the solutions offered by CV, and identify major CV applications in CEA, as well as survey the state of the art in 68 technical papers using deep learning methods.

References

SHOWING 1-10 OF 66 REFERENCES

Proposal-Based Instance Segmentation With Point Supervision

A method called WISE-Net is proposed that only requires point-level annotations for instance segmentation with point- level supervision and obtains competitive results compared to fully-supervised methods in certain scenarios.

Budget-aware Semi-Supervised Semantic and Instance Segmentation

This paper revisits semi-supervised segmentation schemes and narrow down significantly the annotation budget (in terms of total labeling time of the training set) compared to previous approaches and unify weakly and semi- supervised approaches by considering the total annotation budget, thus allowing a fairer comparison between methods.

Semi-supervised Instance Segmentation with a Learned Shape Prior

This work proposes a framework that searches for the target object based on a shape prior that was superior to pre-trained supervised models with access to limited domain-specific training data on all three datasets.

Pointly-Supervised Instance Segmentation

The existing instance segmentation models developed for full mask supervision can be seamlessly trained with point-based supervision collected via the proposed point annotation scheme, which is approximately 5 times faster than annotating full object masks, making high-quality instance segmentations more accessible in practice.

Instance Segmentation of Biological Images Using Harmonic Embeddings

  • V. KulikovV. Lempitsky
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
This work presents a new instance segmentation approach tailored to biological images, where instances may correspond to individual cells, organisms or plant parts, achieving state-of-the-art performance on a popular CVPPP benchmark.

A Positive/Unlabeled Approach for the Segmentation of Medical Sequences using Point-Wise Supervision

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals

A two-step framework that adopts a predetermined mid-level prior in a contrastive optimization objective to learn pixel embeddings and argues about the importance of having a prior that contains information about objects, or their parts, and discusses several possibilities to obtain such a prior in an unsupervised manner.

Semantic Instance Segmentation with a Discriminative Loss Function

This work proposes an approach of combining an off-the-shelf network with a principled loss function inspired by a metric learning objective that encourages a convolutional network to produce a representation of the image that can easily be clustered into instances with a simple post-processing step.

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

This work proposes a new clustering loss function for proposal-free instance segmentation that pulls the spatial embeddings of pixels belonging to the same instance together and jointly learns an instance-specific clustering bandwidth, maximizing the intersection-over-union of the resulting instance mask.

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training.
...