Label conditioned segmentation

• URL: http://arxiv.org/abs/2203.10091v1
• Date: Thu, 17 Mar 2022 22:21:10 GMT
• Title: Label conditioned segmentation
• Authors: Tianyu Ma, Benjamin C. Lee, Mert R. Sabuncu
• Abstract summary: Semantic segmentation is an important task in computer vision that is often tackled with convolutional neural networks (CNNs) For segmentation tasks with multiple classes, the standard approach is to use a network that computes a multi-channel probabilistic segmentation map. We propose a simple yet effective method to address this challenge. In our approach, the segmentation network produces a single-channel output, while being conditioned on a single class label, which determines the output class of the network.
• Score: 14.66405859401613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic segmentation is an important task in computer vision that is often tackled with convolutional neural networks (CNNs). A CNN learns to produce pixel-level predictions through training on pairs of images and their corresponding ground-truth segmentation labels. For segmentation tasks with multiple classes, the standard approach is to use a network that computes a multi-channel probabilistic segmentation map, with each channel representing one class. In applications where the image grid size (e.g., when it is a 3D volume) and/or the number of labels is relatively large, the standard (baseline) approach can become prohibitively expensive for our computational resources. In this paper, we propose a simple yet effective method to address this challenge. In our approach, the segmentation network produces a single-channel output, while being conditioned on a single class label, which determines the output class of the network. Our method, called label conditioned segmentation (LCS), can be used to segment images with a very large number of classes, which might be infeasible for the baseline approach. We also demonstrate in the experiments that label conditioning can improve the accuracy of a given backbone architecture, likely, thanks to its parameter efficiency. Finally, as we show in our results, an LCS model can produce previously unseen fine-grained labels during inference time, when only coarse labels were available during training. We provide all of our code here: https://github.com/tym002/Label-conditioned-segmentation

Related papers

• You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding [107.06117227661204]
  We propose One Thing One Click'', meaning that the annotator only needs to label one point per object. We iteratively conduct the training and label propagation, facilitated by a graph propagation module. Our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy.
  arXiv  Detail & Related papers  (2023-03-26T13:57:00Z)
• Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification [0.0]
  We revisit two popular approaches to multilabel classification: transformer-based heads and labels relations information graph processing branches. Although transformer-based heads are considered to achieve better results than graph-based branches, we argue that with the proper training strategy graph-based methods can demonstrate just a small accuracy drop.
  arXiv  Detail & Related papers  (2022-09-14T12:06:47Z)
• Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models [54.49581189337848]
  We propose a method to enable the end-to-end pre-training for image segmentation models based on classification datasets. The proposed method leverages a weighted segmentation learning procedure to pre-train the segmentation network en masse. Experiment results show that, with ImageNet accompanied by PSSL as the source dataset, the proposed end-to-end pre-training strategy successfully boosts the performance of various segmentation models.
  arXiv  Detail & Related papers  (2022-07-04T13:02:32Z)
• From Explanations to Segmentation: Using Explainable AI for Image Segmentation [1.8581514902689347]
  We build upon the advances of the Explainable AI (XAI) community and extract a pixel-wise binary segmentation. We show that we achieve similar results compared to an established U-Net segmentation architecture. The proposed method can be trained in a weakly supervised fashion, as the training samples must be only labeled on image-level.
  arXiv  Detail & Related papers  (2022-02-01T10:26:10Z)
• Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples [34.97652735163338]
  We propose a novel approach for creating semantic segmentation masks for every object. Our method takes as input the image-level labels of the class categories present in the image. The output of this stage provides pixel-level pseudo-labels, instead of the manual pixel-level labels required by supervised methods.
  arXiv  Detail & Related papers  (2021-12-06T17:32:38Z)
• A Closer Look at Self-training for Zero-Label Semantic Segmentation [53.4488444382874]
  Being able to segment unseen classes not observed during training is an important technical challenge in deep learning. Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models. We propose a consistency regularizer to filter out noisy pseudo-labels by taking the intersections of the pseudo-labels generated from different augmentations of the same image.
  arXiv  Detail & Related papers  (2021-04-21T14:34:33Z)
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization [112.68171734288237]
  We propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. We learn a generative adversarial network that captures the joint image-label distribution and is trained efficiently using a large set of unlabeled images. We demonstrate strong in-domain performance compared to several baselines, and are the first to showcase extreme out-of-domain generalization.
  arXiv  Detail & Related papers  (2021-04-12T21:41:25Z)
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation [78.36781565047656]
  We propose "One Thing One Click," meaning that the annotator only needs to label one point per object. We iteratively conduct the training and label propagation, facilitated by a graph propagation module. Our results are also comparable to those of the fully supervised counterparts.
  arXiv  Detail & Related papers  (2021-04-06T02:27:25Z)
• PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision [12.284208932393073]
  This paper presents a novel procedure for producing semantic segmentation from images given some point level annotations. We propose training a CNN that is normally fully supervised using our pseudo labels in place of ground truth labels. Our method achieves state of the art results for point supervised semantic segmentation on the PASCAL VOC 2012 dataset citeeveringham2010pascal, even outperforming state of the art methods for stronger bounding box and squiggle supervision.
  arXiv  Detail & Related papers  (2020-07-10T21:25:27Z)
• Simple Interactive Image Segmentation using Label Propagation through kNN graphs [0.0]
  This paper proposes a new SSL graph-based interactive image segmentation approach, using undirected and unweighted kNN graphs. It is simpler than many other techniques, but it still achieves classification accuracy in the image segmentation task.
  arXiv  Detail & Related papers  (2020-02-13T18:50:21Z)
• RGB-based Semantic Segmentation Using Self-Supervised Depth Pre-Training [77.62171090230986]
  We propose an easily scalable and self-supervised technique that can be used to pre-train any semantic RGB segmentation method. In particular, our pre-training approach makes use of automatically generated labels that can be obtained using depth sensors. We show how our proposed self-supervised pre-training with HN-labels can be used to replace ImageNet pre-training.
  arXiv  Detail & Related papers  (2020-02-06T11:16:24Z)

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.