Semantic similarity metrics for learned image registration
- URL: http://arxiv.org/abs/2104.10051v1
- Date: Tue, 20 Apr 2021 15:23:58 GMT
- Title: Semantic similarity metrics for learned image registration
- Authors: Steffen Czolbe, Oswin Krause and Aasa Feragen
- Abstract summary: We propose a semantic similarity metric for image registration.
Our approach learns dataset-specific features that drive the optimization of a learning-based registration model.
We train both an unsupervised approach using an auto-encoder, and a semi-supervised approach using supplemental segmentation data to extract semantic features for image registration.
- Score: 10.355938901584565
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose a semantic similarity metric for image registration. Existing
metrics like Euclidean Distance or Normalized Cross-Correlation focus on
aligning intensity values, giving difficulties with low intensity contrast or
noise. Our approach learns dataset-specific features that drive the
optimization of a learning-based registration model. We train both an
unsupervised approach using an auto-encoder, and a semi-supervised approach
using supplemental segmentation data to extract semantic features for image
registration. Comparing to existing methods across multiple image modalities
and applications, we achieve consistently high registration accuracy. A learned
invariance to noise gives smoother transformations on low-quality images.
Related papers
- Deep Semantic Statistics Matching (D2SM) Denoising Network [70.01091467628068]
We introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network.
It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space.
By learning to preserve the semantic distribution of denoised images, we empirically find our method significantly improves the denoising capabilities of networks.
arXiv Detail & Related papers (2022-07-19T14:35:42Z) - Embedding contrastive unsupervised features to cluster in- and
out-of-distribution noise in corrupted image datasets [18.19216557948184]
Using search engines for web image retrieval is a tempting alternative to manual curation when creating an image dataset.
Their main drawback remains the proportion of incorrect (noisy) samples retrieved.
We propose a two stage algorithm starting with a detection step where we use unsupervised contrastive feature learning.
We find that the alignment and uniformity principles of contrastive learning allow OOD samples to be linearly separated from ID samples on the unit hypersphere.
arXiv Detail & Related papers (2022-07-04T16:51:56Z) - Introspective Deep Metric Learning for Image Retrieval [80.29866561553483]
We argue that a good similarity model should consider the semantic discrepancies with caution to better deal with ambiguous images for more robust training.
We propose to represent an image using not only a semantic embedding but also an accompanying uncertainty embedding, which describes the semantic characteristics and ambiguity of an image, respectively.
The proposed IDML framework improves the performance of deep metric learning through uncertainty modeling and attains state-of-the-art results on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.
arXiv Detail & Related papers (2022-05-09T17:51:44Z) - Learning Contrastive Representation for Semantic Correspondence [150.29135856909477]
We propose a multi-level contrastive learning approach for semantic matching.
We show that image-level contrastive learning is a key component to encourage the convolutional features to find correspondence between similar objects.
arXiv Detail & Related papers (2021-09-22T18:34:14Z) - Deep Relational Metric Learning [84.95793654872399]
This paper presents a deep relational metric learning framework for image clustering and retrieval.
We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions.
Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
arXiv Detail & Related papers (2021-08-23T09:31:18Z) - A low-rank representation for unsupervised registration of medical
images [10.499611180329804]
We propose a novel approach based on a low-rank representation, i.e., Regnet-LRR, to tackle the problem of noisy data registration scenarios.
We show that the low-rank representation can boost the ability and robustness of models as well as bring significant improvements in noisy data registration scenarios.
arXiv Detail & Related papers (2021-05-20T07:04:10Z) - A Hierarchical Transformation-Discriminating Generative Model for Few
Shot Anomaly Detection [93.38607559281601]
We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image.
The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions.
arXiv Detail & Related papers (2021-04-29T17:49:48Z) - DeepSim: Semantic similarity metrics for learned image registration [6.789370732159177]
We propose a semantic similarity metric for image registration.
Our approach learns dataset-specific features that drive the optimization of a learning-based registration model.
arXiv Detail & Related papers (2020-11-11T12:35:07Z) - Deep Group-wise Variational Diffeomorphic Image Registration [3.0022455491411653]
We propose to extend current learning-based image registration to allow simultaneous registration of multiple images.
We present a general mathematical framework that enables both registration of multiple images to their viscous geodesic average and registration in which any of the available images can be used as a fixed image.
arXiv Detail & Related papers (2020-10-01T07:37:28Z) - Data-driven Meta-set Based Fine-Grained Visual Classification [61.083706396575295]
We propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition.
Specifically, guided by a small amount of clean meta-set, we train a selection net in a meta-learning manner to distinguish in- and out-of-distribution noisy images.
arXiv Detail & Related papers (2020-08-06T03:04:16Z) - CoMIR: Contrastive Multimodal Image Representation for Registration [4.543268895439618]
We propose contrastive coding to learn shared, dense image representations, referred to as CoMIRs (Contrastive Multimodal Image Representations)
CoMIRs enable the registration of multimodal images where existing registration methods often fail due to a lack of sufficiently similar image structures.
arXiv Detail & Related papers (2020-06-11T10:51:33Z)
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.