Learning to segment from object sizes
- URL: http://arxiv.org/abs/2207.00289v1
- Date: Fri, 1 Jul 2022 09:34:44 GMT
- Title: Learning to segment from object sizes
- Authors: Denis Baru\v{c}i\'c (1), Jan Kybic (1) ((1) Czech Technical University
in Prague, Czech Republic)
- Abstract summary: We propose an algorithm for training a deep segmentation network from a dataset of a few pixel-wise annotated images and many images with known object sizes.
The algorithm minimizes a discrete (non-differentiable) loss function defined over the object sizes by sampling the gradient and then using the standard back-propagation algorithm.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep learning has proved particularly useful for semantic segmentation, a
fundamental image analysis task. However, the standard deep learning methods
need many training images with ground-truth pixel-wise annotations, which are
usually laborious to obtain and, in some cases (e.g., medical images), require
domain expertise. Therefore, instead of pixel-wise annotations, we focus on
image annotations that are significantly easier to acquire but still
informative, namely the size of foreground objects. We define the object size
as the maximum distance between a foreground pixel and the background. We
propose an algorithm for training a deep segmentation network from a dataset of
a few pixel-wise annotated images and many images with known object sizes. The
algorithm minimizes a discrete (non-differentiable) loss function defined over
the object sizes by sampling the gradient and then using the standard
back-propagation algorithm. We study the performance of our approach in terms
of training time and generalization error.
Related papers
- Learning Semantic Segmentation with Query Points Supervision on Aerial Images [57.09251327650334]
We present a weakly supervised learning algorithm to train semantic segmentation algorithms.
Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation.
arXiv Detail & Related papers (2023-09-11T14:32:04Z) - Beyond pixel-wise supervision for segmentation: A few global shape
descriptors might be surprisingly good! [16.293620755563854]
Standard losses for training deep segmentation networks could be seen as individual classifications of pixels, instead of supervising the global shape of the predicted segmentations.
This study investigates how effective global geometric shape descriptors could be, when used on their own as segmentation losses for training deep networks.
arXiv Detail & Related papers (2021-05-03T13:44:36Z) - Sparse Object-level Supervision for Instance Segmentation with Pixel
Embeddings [4.038011160363972]
Most state-of-the-art instance segmentation methods have to be trained on densely annotated images.
We propose a proposal-free segmentation approach based on non-spatial embeddings.
We evaluate the proposed method on challenging 2D and 3D segmentation problems in different microscopy modalities.
arXiv Detail & Related papers (2021-03-26T16:36:56Z) - Scale Normalized Image Pyramids with AutoFocus for Object Detection [75.71320993452372]
A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales.
We propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects.
The resulting algorithm is referred to as AutoFocus and results in a 2.5-5 times speed-up during inference when used with SNIP.
arXiv Detail & Related papers (2021-02-10T18:57:53Z) - Exploring Cross-Image Pixel Contrast for Semantic Segmentation [130.22216825377618]
We propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting.
The core idea is to enforce pixel embeddings belonging to a same semantic class to be more similar than embeddings from different classes.
Our method can be effortlessly incorporated into existing segmentation frameworks without extra overhead during testing.
arXiv Detail & Related papers (2021-01-28T11:35:32Z) - Rethinking of the Image Salient Object Detection: Object-level Semantic
Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter [62.26677215668959]
We propose a lightweight, weakly supervised deep network to coarsely locate semantically salient regions.
We then fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement.
Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.
arXiv Detail & Related papers (2020-08-10T07:12:43Z) - Learning RGB-D Feature Embeddings for Unseen Object Instance
Segmentation [67.88276573341734]
We propose a new method for unseen object instance segmentation by learning RGB-D feature embeddings from synthetic data.
A metric learning loss function is utilized to learn to produce pixel-wise feature embeddings.
We further improve the segmentation accuracy with a new two-stage clustering algorithm.
arXiv Detail & Related papers (2020-07-30T00:23:07Z) - Multi-task deep learning for image segmentation using recursive
approximation tasks [5.735162284272276]
Deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create.
In this work, we develop a multi-task learning method to relax this constraint.
The network is trained on an extremely small amount of precisely segmented images and a large set of coarse labels.
arXiv Detail & Related papers (2020-05-26T21:35:26Z) - Reinforced Coloring for End-to-End Instance Segmentation [10.73460247817528]
We propose a novel iterative deep reinforcement learning agent that learns how to differentiate multiple objects in parallel.
Our reward function for the trainable agent is designed to favor grouping pixels belonging to the same object using a graph coloring algorithm.
arXiv Detail & Related papers (2020-05-14T15:15:47Z) - Distilling Localization for Self-Supervised Representation Learning [82.79808902674282]
Contrastive learning has revolutionized unsupervised representation learning.
Current contrastive models are ineffective at localizing the foreground object.
We propose a data-driven approach for learning in variance to backgrounds.
arXiv Detail & Related papers (2020-04-14T16:29:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.