In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image serves as supervision for its strongly perturbed version.
To address the task, we first analyze the theory of the multi-domain learning, which highlights that 1) mitigating the impact of domain gap and 2) exploiting all samples to train the model can effectively reduce the generalization error in each source domain so as to improve the quality of pseudo-labels.
In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-supervised learning (SSL), which is a hyperparameter-free framework that is independent of confidence threshold and works with both the matched (conventionally) and the mismatched class distributions.
We demonstrate the performance of our method on two public generalizable segmentation benchmarks in medical images, which validates our method could achieve the state-of-the-art performance.
Besides, for the label distribution of each class, we further revise it to give more and equal attention to the other domains that the class does not belong to, which can effectively reduce the domain gap across different domains and obtain the domain-invariant feature.
The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples.
Different from the conventional data augmentation, the proposed domain-aware mix-normalization to enhance the diversity of features during training from the normalization view of the neural network, which can effectively alleviate the model overfitting to the source domains, so as to boost the generalization capability of the model in the unseen domain.
For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain?
Besides, we leverage the progressive scheme to add the ratio of the dropout during training, which can gradually boost the difficulty of training model to enhance the robustness of the model.
A significance of our work lies in that it shows the potential of unsupervised domain generalization for person ReID and sets a strong baseline for the further research on this topic.
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.
Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process.
Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.
Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.
In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student.
As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption.
Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes.
Ranked #27 on Few-Shot Semantic Segmentation on PASCAL-5i (5-Shot)
How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world.
These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images.
Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.
In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.
To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains.
Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model learn more robust feature representations.
In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up.
Robust segmentation for non-elongated tissues in medical images is hard to realize due to the large variation of the shape, size, and appearance of these tissues in different patients.
Semantic segmentation in a supervised learning manner has achieved significant progress in recent years.
Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation.
Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.
To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.
By introducing an unified optimization goal, DeepAugNet intends to combine the data augmentation and the deep model training in an end-to-end training manner which is realized by simultaneously training a hybrid architecture of dueling deep Q-learning algorithm and a surrogate deep model.
In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels.
Moreover, in the training process, we adopt the joint learning scheme to simultaneously train each branch by the independent loss function, which can enhance the generalization ability of each branch.
To achieve the camera alignment, we develop a Multi-Camera Adversarial Learning (MCAL) to map images of different cameras into a shared subspace.
For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains.
Ranked #18 on Unsupervised Domain Adaptation on Market to Duke
Furthermore, in a progressively and nonlinearly learning way, ODML has a stronger learning ability than traditional shallow online metric learning in the case of limited available training data.
Due to the irregular motion, similar appearance and diverse shape, accurate segmentation of kidney tumor in CT images is a difficult and challenging task.
In this paper, we present a novel method for interactive medical image segmentation with the following merits.
Lastly, considering person retrieval is a special image retrieval task, we propose a novel ranking loss to optimize the whole network.
We delete those species with only one living environment image from data set, then partition the rest images from living environment into two subsets, one used as test subset, the other as training subset respectively combined with all standard pattern butterfly images or the standard pattern butterfly images with the same species of the images from living environment.
The proposed method has been tested on multiple SPD-based visual representation data sets used in the literature, and the results demonstrate its interesting properties and attractive performance.
In this paper, a new caricature dataset is built, with the objective to facilitate research in caricature recognition.
To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper.
Therefore, it is natural to hypothesize that the low-level features extracted from neuroimaging data are related to each other in some ways.
Specifically, to segment the prostate in the current treatment image, the physician first takes a few seconds to manually specify the first and last slices of the prostate in the image space.