Search Results for author:
Found 70 papers, 38 papers with code
LibFewShot: A Comprehensive Library for Few-shot Learning
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.
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
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.
Semi-supervised Change Detection
Semi-supervised Medical Image Segmentation
+1
ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
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.
FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
Then, we investigate the role of synthetic images by joint training with real images, or pre-training for real images.
Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization
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?
MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization
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.
RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning
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.
Towards Semi-supervised Learning with Non-random Missing Labels
Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data.
Mining Latent Classes for Few-shot Segmentation
Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes.
Ranked #41 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation
Subsequently, by introducing unlabeled volumes, we propose a dual-network paradigm named Dense-Sparse Co-training (DeSCO) that exploits dense pseudo labels in early stage and sparse labels in later stage and meanwhile forces consistent output of two networks.
Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning
To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain samples.
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain.
Manifold Alignment for Semantically Aligned Style Transfer
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.
ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization
However, the local operation of the convolution kernel makes the model focus too much on local representations (e. g., texture), which inherently causes the model more prone to overfit to the source domains and hampers its generalization ability.
DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization
Deep Neural Networks have exhibited considerable success in various visual tasks.
Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.
DomainAdaptor: A Novel Approach to Test-time Adaptation
To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test.
Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration
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.
Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization
Semantic segmentation in a supervised learning manner has achieved significant progress in recent years.
Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
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.
Data Augmentation
Unsupervised Few-Shot Image Classification
+1
Interactive Medical Image Segmentation via Point-Based Interaction and Sequential Patch Learning
In this paper, we present a novel method for interactive medical image segmentation with the following merits.
3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks
Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains.
Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning
Sample adaptive augmentation (SAA) is proposed for this stated purpose and consists of two modules: 1) sample selection module; 2) sample augmentation module.
Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.
MVDG: A Unified Multi-view Framework for Domain Generalization
Beyond the training stage, overfitting could also cause unstable prediction in the test stage.
Automatic Data Augmentation by Learning the Deterministic Policy
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.
Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
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.
PLN: Parasitic-Like Network for Barely Supervised Medical Image Segmentation
In this paper, by introducing an extremely sparse annotation way of labeling only one slice per 3D image, we investigate a novel barely-supervised segmentation setting with only a few sparsely-labeled images along with a large amount of unlabeled images.
Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework
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.
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning
While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e. g., fine-grained visual classification in the context of SSL (SS-FGVC).
PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization
Particularly, the proposed method can generate a variety of data variants to better deal with the overfitting issue.
Concatenate, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation
Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations.
SETA: Semantic-Aware Token Augmentation for Domain Generalization
In this paper, we study the impact of prior CNN-based augmentation methods on token-based models, revealing their performance is suboptimal due to the lack of incentivizing the model to learn holistic shape information.
Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation
To fully utilize the information within the intermediate domain, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to unlabeled data by merging pseudo labels from intermediate samples.
A Multilayer Framework for Online Metric Learning
Furthermore, in a progressively and nonlinearly learning way, MLOML has a stronger learning ability than traditional online metric learning in the case of limited available training data.
PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance
Based on this technique, we assign appropriate training weights to unlabeled data to enhance the construction of a discriminative latent space.
Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations
2) From the feature perspective, the simple Tail Interaction module implicitly enhances potential correlations among all samples from all source domains, facilitating the acquisition of domain-invariant representations across multiple domains for the model.
Crossbar-Net: A Novel Convolutional Network for Kidney Tumor Segmentation in CT Images
Due to the irregular motion, similar appearance and diverse shape, accurate segmentation of kidney tumor in CT images is a difficult and challenging task.
MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
Lastly, considering person retrieval is a special image retrieval task, we propose a novel ranking loss to optimize the whole network.
The Automatic Identification of Butterfly Species
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.
WebCaricature: a benchmark for caricature recognition
In this paper, a new caricature dataset is built, with the objective to facilitate research in caricature recognition.
OPML: A One-Pass Closed-Form Solution for Online Metric Learning
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.
Prostate Segmentation in CT Images via Spatial-Constrained Transductive Lasso
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.
Joint Coupled-Feature Representation and Coupled Boosting for AD Diagnosis
Therefore, it is natural to hypothesize that the low-level features extracted from neuroimaging data are related to each other in some ways.
Revisiting Metric Learning for SPD Matrix Based Visual Representation
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.
A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
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 #19 on
Unsupervised Domain Adaptation
on Market to Duke
Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
To achieve the camera alignment, we develop a Multi-Camera Adversarial Learning (MCAL) to map images of different cameras into a shared subspace.
GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification
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.
Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
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.
Differentiable Meta-learning Model for Few-shot Semantic Segmentation
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.
Asymmetric Distribution Measure for Few-shot Learning
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.
Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation
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.
Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation
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.
Class Distribution Alignment for Adversarial Domain Adaptation
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.
Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective
Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.
Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation
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.
A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
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.
Feature-based Style Randomization for Domain Generalization
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.
Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization
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.
A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification
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.
Label Distribution Learning for Generalizable Multi-source Person Re-identification
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.
DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning
Consistency-based Semi-supervised learning (SSL) has achieved promising performance recently.
MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization
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.
Patch-aware Batch Normalization for Improving Cross-domain Robustness
By exploiting the differences between local patches of an image, our proposed PBN can effectively enhance the robustness of the model's parameters.
Generalizable Metric Network for Cross-domain Person Re-identification
Additionally, we introduce the Dropout-based Perturbation (DP) module to enhance the generalization capability of the metric network by enriching the sample-pair diversity.
NormAUG: Normalization-guided Augmentation for Domain Generalization
Our method includes two paths: the main path and the auxiliary (augmented) path.
A Novel Cross-Perturbation for Single Domain Generalization
Horizontally, it applies image-level and feature-level perturbations to enhance the diversity of the training data, mitigating the issue of limited diversity in single-source domains.
A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness
Although having attributed it to training dynamics, existing theoretical explanations of activation sparsity are restricted to shallow networks, small training steps and special training, despite its emergence in deep models standardly trained for a large number of steps.
Exploring Flat Minima for Domain Generalization with Large Learning Rates
Instead, we observe that leveraging a large learning rate can simultaneously promote weight diversity and facilitate the identification of flat regions in the loss landscape.
