KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation

• URL: http://arxiv.org/abs/2106.06237v1
• Date: Fri, 11 Jun 2021 08:43:59 GMT
• Title: KRADA: Known-region-aware Domain Alignment for Open World Semantic Segmentation
• Authors: Chenhong Zhou, Feng Liu, Chen Gong, Tongliang Liu, Bo Han, William Cheung
• Abstract summary: In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image. In an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images. We propose an end-to-end learning framework, known-region-aware domain alignment (KRADA), to distinguish unknown classes while aligning distributions of known classes in labeled and unlabeled open-world images.
• Score: 64.03817806316903
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image, where labeled training images and unlabeled test images are from the same distribution and share the same label set. However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images. Hence, in this paper, we consider a new, more realistic, and more challenging problem setting where the pixel-level classifier has to be trained with labeled images and unlabeled open-world images -- we name it open world semantic segmentation (OSS). In OSS, the trained classifier is expected to identify unknown-class pixels and classify known-class pixels well. To solve OSS, we first investigate which distribution that unknown-class pixels obey. Then, motivated by the goodness-of-fit test, we use statistical measurements to show how a pixel fits the distribution of an unknown class and select highly-fitted pixels to form the unknown region in each image. Eventually, we propose an end-to-end learning framework, known-region-aware domain alignment (KRADA), to distinguish unknown classes while aligning distributions of known classes in labeled and unlabeled open-world images. The effectiveness of KRADA has been verified on two synthetic tasks and one COVID-19 segmentation task.

Related papers

• Learning to Detect Semantic Boundaries with Image-level Class Labels [14.932318540666548]
  This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating coarse areas of object classes through attentions drawn by an image classification network. We design a new neural network architecture that can learn to estimate semantic boundaries reliably even with uncertain supervision.
  arXiv  Detail & Related papers  (2022-12-15T01:56:22Z)
• Probabilistic Deep Metric Learning for Hyperspectral Image Classification [91.5747859691553]
  This paper proposes a probabilistic deep metric learning framework for hyperspectral image classification. It aims to predict the category of each pixel for an image captured by hyperspectral sensors. Our framework can be readily applied to existing hyperspectral image classification methods.
  arXiv  Detail & Related papers  (2022-11-15T17:57:12Z)
• Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [70.36722026729859]
  We propose a dual-perspective semantic-aware representation blending (DSRB) that blends multi-granularity category-specific semantic representation across different images. The proposed DS consistently outperforms current state-of-the-art algorithms on all proportion label settings.
  arXiv  Detail & Related papers  (2022-05-26T00:33:44Z)
• GOSS: Towards Generalized Open-set Semantic Segmentation [38.00665104750745]
  We present and study a new image segmentation task, called Generalized Open-set Semantic (GOSS) GOSS classifies pixels as belonging to known classes, and clusters (or groups) of pixels of unknown class are labelled as such. We believe our new GOSS task can produce an expressive image understanding for future research.
  arXiv  Detail & Related papers  (2022-03-23T01:03:06Z)
• Generalized Category Discovery [148.32255950504182]
  We consider a highly general image recognition setting wherein, given a labelled and unlabelled set of images, the task is to categorize all images in the unlabelled set. Here, the unlabelled images may come from labelled classes or from novel ones. We first establish strong baselines by taking state-of-the-art algorithms from novel category discovery and adapting them for this task. We then introduce a simple yet effective semi-supervised $k$-means method to cluster the unlabelled data into seen and unseen classes.
  arXiv  Detail & Related papers  (2022-01-07T18:58:35Z)
• Mixed Supervision Learning for Whole Slide Image Classification [88.31842052998319]
  We propose a mixed supervision learning framework for super high-resolution images. During the patch training stage, this framework can make use of coarse image-level labels to refine self-supervised learning. A comprehensive strategy is proposed to suppress pixel-level false positives and false negatives.
  arXiv  Detail & Related papers  (2021-07-02T09:46:06Z)
• Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning [28.498782661888775]
  We formulate weakly supervised segmentation as a semi-supervised metric learning problem. We propose 4 types of contrastive relationships between pixels and segments in the feature space. We deliver a universal weakly supervised segmenter with significant gains on Pascal VOC and DensePose.
  arXiv  Detail & Related papers  (2021-05-03T15:49:01Z)
• 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)
• Deep Active Learning for Joint Classification & Segmentation with Weak Annotator [22.271760669551817]
  CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions. We propose an active learning framework, which progressively integrates pixel-level annotations during training. Our results indicate that, by simply using random sample selection, the proposed approach can significantly outperform state-of-the-art CAMs and AL methods.
  arXiv  Detail & Related papers  (2020-10-10T03:25:54Z)

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.