Robust Label Research Articles

Robust PUF Label Authentication System Synergistically Constructed by Hierarchical Pattern of Self‐assembled Phase‐Separation Encrypted Wrinkle and Deep Learning Model

AbstractWith the increasing demand for information security, current anti‐counterfeiting methods not only suffer from issues such as low information density and vulnerability to forgery, but also inherently involve a trade‐off between information capacity and readout methods. This paper reports a high‐security solution using hierarchical pattern with perfect combination of micro self‐wrinkle and nano phase‐separation as physical unclonable function (PUF) labels, which is generated through self‐organization of anthracene‐functionalized poly(styrene‐block‐butadiene‐block‐styrene) (SBS‐CAN) under UV exposure. The double‐layer morphologies formed by the wrinkle and phase separation are adjustable, independent, and stable. The obtained hierarchical PUF labels exhibit random and unique features similar to the minutiae of fingerprints at both micro and nano scales, ensuring a well‐balanced bit uniformity (>0.492), high uniqueness (>0.496), and outstanding reliability (>96%). As a consequence of the multi‐layered combination of morphologies, the designed PUF label possesses an information density about 1010 times higher than that of human fingerprints. The PUF labels can be quickly obtained through simple visual scanning and exhibit sufficient security. To cope with various application environments, the advanced authentication pipeline designed LPLA guarantees robust label recognition capability in real‐world scenarios. A practical integrated anti‐counterfeiting authentication system is developed by combining hierarchical PUF labels and authentication pipeline.

Discriminative label correlation based robust structure learning for multi-label feature selection

Feature selection is a key technique to tackle the curse of dimensionality in multi-label learning. Lots of embedded multi-label feature selection methods have been developed. However, they face challenges in identifying and excluding redundant features. To address these issues, this paper proposes a multi-label feature selection method that combines robust structural learning and discriminative label regularization. The proposed method starts from the feature space rather than data space, motivated by the principle that redundant features have high similarity or strong correlation. To exclude redundant features, a regularization on the feature selection matrix is designed by combining ℓ2,1-norm penalty with inner products of feature weight vectors. This regularization can help to learn a robust structure in the feature selection matrix. Meanwhile, both of the similarity and dissimilarity of labels of instances are involved in exploring discriminative label correlations. Extensive experiments verified the effectiveness of the proposed model for feature selection.

PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning.

Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set with the ground-truth label included. However, in a more practical but challenging scenario, the annotator may miss the ground-truth and provide a wrong candidate set, which is known as the noisy PLL problem. To remedy this problem, we propose the PiCO+ framework that simultaneously disambiguates the candidate sets and mitigates label noise. Core to PiCO+, we develop a novel label disambiguation algorithm PiCO that consists of a contrastive learning module along with a novel class prototype-based disambiguation method. Theoretically, we show that these two components are mutually beneficial, and can be rigorously justified from an expectation-maximization (EM) algorithm perspective. To handle label noise, we extend PiCO to PiCO+, which further performs distance-based clean sample selection, and learns robust classifiers by a semi-supervised contrastive learning algorithm. Beyond this, we further investigate the robustness of PiCO+ in the context of out-of-distribution noise and incorporate a novel energy-based rejection method for improved robustness. Extensive experiments demonstrate that our proposed methods significantly outperform the current state-of-the-art approaches in standard and noisy PLL tasks and even achieve comparable results to fully supervised learning.

Abstract 5492: Spatial organization and cellular composition of immunity hubs in human colorectal cancer

Abstract Background: Among colorectal cancer (CRC) tumors, mismatch repair deficient (MMRd) tumors have more immunogenic neo-antigens, hence more cytotoxic T-cell mediated anti-tumor immunity than mismatch repair proficient (MMRp) tumors. Previously1, we transcriptionally profiled over 300,000 cells from 62 MMRd and MMRp CRC tumors and found an MMRd-unique network of immunologically active transcriptional states enriched in interferon-stimulated genes (ISGs). With 4-color imaging, we showed that this program arises from spatially organized hubs of at least 3 cell types: IFNã-secreting T and interferon-responsive CXCL9/10/11+ myeloid and tumor cells. To characterize the breadth of cells involved in tumor immunity hubs, we must simultaneously measure the expression of 100s of genes in situ. Methods: To describe the cellular composition, structural organization and intercellular spatial interactions of these immunity hubs, we profiled primary untreated resection specimens from 17 CRC donors (n=12 MMRd, 5 MMRp) using multiplexed error-robust FISH (MERFISH) mRNA microscopy. Efforts were made to sample both the tumor body and the invasive border of the tumor. We designed a panel of 479 genes to capture key transcriptional programs from our single-cell atlas1. We wrote analytical pipelines to segment transcripts into cells, select high-quality cells, and organize cells into distinct zones in tissue. To leverage the rich information in the scRNA-seq atlas1, we designed a robust label transfer analysis to assign cell state labels to MERFISH cells by comparison to scRNAseq cells. Results: We profiled 7.5 million high quality MERFISH cells across 21 CRC tissue sections and labeled the cells into 7 major lineages: 63.19% epithelial, 22.52% stromal, 7.75% myeloid, 3.72% T/NK/ILCs, 1.45% plasma, 1.2% B, and 0.17% mast cells. We visualized the spatial location of these cell types. T cells aggregated into 3 distinct regions of tissue: tertiary lymphoid structures (TLS) outside the tumor, and smaller clusters near the invasive border and in the tumor center. We identified immunity hubs defined by colocalized CXCL9/10/11 expressing cells and T cells near the invasive border and in the center of MMRd tumors. As expected, we found enrichment of CXCL13, IFNG, and ISGs such as CD74 and MHCII genes at these locations. In contrast, we found evidence of CCL17+CCL19+LAMP3+ activated dendritic cells and B cells enriched in the TLS. These results support a distinct composition and localization of immunity hubs in tumors, in contrast to TLS outside tumors. Conclusions: Our study defines the composition, spatial organization, and intercellular interactions of immunity hubs, shedding light on the anti-tumor immune response in CRC. Ethics Approval: Approved by the DF/HCC Institutional Review Board (protocol #02-240).(1) Pelka, K. et al. Spatially organized multicellular immune hubs in human colorectal cancer. Cell 184, 4734-4752.e20 (2021) Citation Format: Mukta G. Palshikar, Maxwell Spurrell, Jack Demaray, Han Chen, Scott Engels, Roopa Madhu, Milan Parikh, Izabella Gazmora, Arnav Mehta, Nicolas Fernandez, Colles Price, Jiang He, Sonia Cohen, Karin Pelka, Nir Hacohen, Jonathan Chen, Ilya Korsunsky. Spatial organization and cellular composition of immunity hubs in human colorectal cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 5492.

Robust Label Propagation and Graph Embedding for Cross-Domain Image Classification

Robust Label Propagation and Graph Embedding for Cross-Domain Image Classification

Robust Label and Feature Space Co-Learning for Multi-Label Classification

Multi-label classification remains a challenging task for high-dimensional data samples and their labels both increase the complexity of training models. In this paper, we propose a Robust Label and Feature Space Co-Learning method, referred to as RLFSCL, for multi-label classification. Different from traditional multi-label classification methods which focus on feature space learning through regression directly between data samples and labels, our proposed method can further learn robust low rank label space from this traditional regression method. Therefore, our RLFSCL can learn better low rank feature and label representations simultaneously in original noisy and high dimensional spaces. Experimental comparison on five benchmark datasets, including Rcv1s5, Cal500, and Corel16k4 shows that the proposed RLFSCL algorithm outperforms state-of-the-art multi-label classification methods. The code of RLFSCL is made available on <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/JingChuanTang/RLFSCL.</uri>

Weakly supervised fine-grained semantic segmentation via spatial correlation-guided learning

Weakly supervised semantic segmentation (WSSS) mainly adopts class activation map (CAM) to recognize different categories with generated pseudo masks of only image-level labels. Recently, many advanced works focus on learning the semantic correlation to refine the conventional CAM, which only identify sparse and discriminative semantic regions, severely weakening the further learning ability of spatial features. To copy with the above problem, a spatial correlation-guided learning framework is proposed to exploit the spatial and semantic correlation between adjacent pixels for weakly supervised fine-grained semantic segmentation (WSFGSS). From the spatial perspective, self-supervised multi-view clustering (SMC) is designed to fully mine spatial correlation by clustering of multiple views including scale, angle and position. Moreover, a hybrid self-supervised (HS) loss function is used to further promote the optimized speed and accuracy of three spatial representations. From the semantic perspective, the affinity matrix is applied to describe the semantic similarity between different pixels by building a weighted graph, and combine above robust pseudo label into a probability transition matrix. Therefore, the initial CAM is gradually corrected during the iterative optimization by the random walk algorithm. Finally, the refined CAM is utilized as supervision information for training the standard segmentation network effectively. Sufficient experimental results on BSDS500, PASCAL VOC 2012 and MS COCO datasets show that the proposed SMC method obtains more accurate pseudo labels than the recent unsupervised segmentation models. Meantime, with these pseudo labels, the proposed fine-grained framework achieves the state-of-the-art performance for WSFGSS.

ScNCL: transferring labels from scRNA-seq to scATAC-seq data with neighborhood contrastive regularization.

scATAC-seq has enabled chromatin accessibility landscape profiling at the single-cell level, providing opportunities for determining cell-type-specific regulation codes. However, high dimension, extreme sparsity, and large scale of scATAC-seq data have posed great challenges to cell-type identification. Thus, there has been a growing interest in leveraging the well-annotated scRNA-seq data to help annotate scATAC-seq data. However, substantial computational obstacles remain to transfer information from scRNA-seq to scATAC-seq, especially for their heterogeneous features. We propose a new transfer learning method, scNCL, which utilizes prior knowledge and contrastive learning to tackle the problem of heterogeneous features. Briefly, scNCL transforms scATAC-seq features into gene activity matrix based on prior knowledge. Since feature transformation can cause information loss, scNCL introduces neighborhood contrastive learning to preserve the neighborhood structure of scATAC-seq cells in raw feature space. To learn transferable latent features, scNCL uses a feature projection loss and an alignment loss to harmonize embeddings between scRNA-seq and scATAC-seq. Experiments on various datasets demonstrated that scNCL not only realizes accurate and robust label transfer for common types, but also achieves reliable detection of novel types. scNCL is also computationally efficient and scalable to million-scale datasets. Moreover, we prove scNCL can help refine cell-type annotations in existing scATAC-seq atlases. The source code and data used in this paper can be found in https://github.com/CSUBioGroup/scNCL-release.

New User Intent Discovery With Robust Pseudo Label Training and Source Domain Joint Training

New User Intent Discovery With Robust Pseudo Label Training and Source Domain Joint Training

Two Wrongs Don’t Make a Right: Combating Confirmation Bias in Learning with Label Noise

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could result in a loss of information, especially when the corruption has a dependency on data, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: pseudo-labels fail to correct a considerable amount of noisy labels, and consequently, the errors accumulate. To sufficiently exploit information from noisy labels and mitigate wrong corrections, we propose Robust Label Refurbishment (Robust LR)—a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels. We show that our method successfully alleviates the damage of both label noise and confirmation bias. As a result, it achieves state-of-the-art performance across datasets and noise types, namely CIFAR under different levels of synthetic noise and mini-WebVision and ANIMAL-10N with real-world noise.

Robust co-teaching learning with consistency-based noisy label correction for medical image classification.

Deep neural networks (DNNs) have made great achievements in computer-aided diagnostic systems, but the success highly depends on massive data with high-quality labels. However, for many medical image datasets, a considerable number of noisy labels are introduced by inter- and intra-observer variability, thus hampering DNNs' performance. To address this problem, a robust noisy label correction method with the co-teaching learning paradigm is proposed. The proposed method aims to reduce the effect of noisy labels by correcting or removing them. It consists of two modules. An adaptive noise rate estimation module is employed to calculate the dataset's noise rate, which is helpful to detect noisy labels but is usually unavailable in clinical applications. A consistency-based noisy label correction module aims to detect noisy labels and correct them to reduce the disturbance from noisy labels and exploit useful information in data. Experiments are conducted on the public skin lesion dataset ISIC-2017, ISIC-2019, and our constructed thyroid ultrasound image dataset. The results demonstrate that the proposed method outperforms other noisy label learning methods in medical image classification tasks. It is also evaluated on the natural image dataset CIFAR-10 to show its generalization. This paper proposes a noisy label correction method to handle noisy labels in medical image datasets. Experimental results show that it can self-adapt to different datasets and efficiently correct noisy labels, which is suitable for medical image classification.

Background context affects word-object mapping.

Children encounter new words across variable and noisy contexts. This variability may affect word learning, but the literature includes discrepant findings. The current experiment investigated one source of these discrepant findings: whether contexts with familiar, nameable objects are associated with less robust label learning. Two year olds were exposed to word-object pairings on variable contexts that either included nameable objects or did not. Target selection was more robust when exposure occurred without other nameable objects. The difference was present immediately, but not after a delay. This study provides the evidence that context effects are context-bound.

Robust multi-label feature selection with shared label enhancement

Feature selection has attracted considerable attention due to the wide application of multi-label learning. However, previous methods do not fully consider the relationship between feature sets and label sets but devote attention to either of them. Furthermore, conventional multi-label learning utilizes logical labels to estimate relevance between feature sets and label sets so that the importance of corresponding labels cannot be well reflected. Additionally, numerous irrelevant and redundant labels degrade the classification performance of models. To this end, we propose a multi-label feature selection method named Robust multi-label Feature Selection with shared Label Enhanced (RLEFS). First, we obtain a robust label enhancement term by reconstructing labels from logical labels to numerical labels and imposing \(l_{2,1}\)-norm onto the label enhancement term. Second, RLEFS utilizes the robust label enhancement term to share the similar latent semantic structure between feature matrix and label matrix. Third, local structure is considered to ensure the consistency of label information during the feature selection process. Finally, we integrate the above terms into one joint learning framework, and then, a simple but effective optimization method with provable convergence is proposed to solve RLEFS. Experimental results demonstrate the classification superiority of RLEFS in comparison with seven state-of-the-art methods.

Scene Changes Understanding Framework Based on Graph Convolutional Networks and Swin Transformer Blocks for Monitoring LCLU Using High-Resolution Remote Sensing Images

High-resolution remote sensing images with rich land surface structure can provide data support for accurately understanding more detailed change information of land cover and land use (LCLU) at different times. In this study, we present a novel scene change understanding framework for remote sensing which includes scene classification and change detection. To enhance the feature representation of images in scene classification, a robust label semantic relation learning (LSRL) network based on EfficientNet is presented for scene classification. It consists of a semantic relation learning module based on graph convolutional networks and a joint expression learning framework based on similarity. Since the bi-temporal remote sensing image pairs include spectral information in both temporal and spatial dimensions, land cover and land use change monitoring can be improved by using the relationship between different spatial and temporal locations. Therefore, a change detection method based on swin transformer blocks (STB-CD) is presented to obtain contextual relationships between targets. The experimental results on the LEVIR-CD, NWPU-RESISC45, and AID datasets demonstrate the superiority of LSRL and STB-CD over other state-of-the-art methods.

Robust Multi-Label Classification with Enhanced Global and Local Label Correlation

Data representation is of significant importance in minimizing multi-label ambiguity. While most researchers intensively investigate label correlation, the research on enhancing model robustness is preliminary. Low-quality data is one of the main reasons that model robustness degrades. Aiming at the cases with noisy features and missing labels, we develop a novel method called robust global and local label correlation (RGLC). In this model, subspace learning reconstructs intrinsic latent features immune from feature noise. The manifold learning ensures that outputs obtained by matrix factorization are similar in the low-rank latent label if the latent features are similar. We examine the co-occurrence of global and local label correlation with the constructed latent features and the latent labels. Extensive experiments demonstrate that the classification performance with integrated information is statistically superior over a collection of state-of-the-art approaches across numerous domains. Additionally, the proposed model shows promising performance on multi-label when noisy features and missing labels occur, demonstrating the robustness of multi-label classification.

RNMFLP: Predicting circRNA-disease associations based on robust nonnegative matrix factorization and label propagation.

Circular RNAs (circRNAs) are a class of structurally stable endogenous noncoding RNA molecules. Increasing studies indicate that circRNAs play vital roles in human diseases. However, validating disease-related circRNAs in vivo is costly and time-consuming. A reliable and effective computational method to identify circRNA-disease associations deserves further studies. In this study, we propose a computational method called RNMFLP that combines robust nonnegative matrix factorization (RNMF) and label propagation algorithm (LP) to predict circRNA-disease associations. First, to reduce the impact of false negative data, the original circRNA-disease adjacency matrix is updated by matrix multiplication using the integrated circRNA similarity and the disease similarity information. Subsequently, the RNMF algorithm is used to obtain the restricted latent space to capture potential circRNA-disease pairs from the association matrix. Finally, the LP algorithm is utilized to predict more accurate circRNA-disease associations from the integrated circRNA similarity network and integrated disease similarity network, respectively. Fivefold cross-validation of four datasets shows that RNMFLP is superior to the state-of-the-art methods. In addition, case studies on lung cancer, hepatocellular carcinoma and colorectal cancer further demonstrate the reliability of our method to discover disease-related circRNAs.

Semi-Supervised Superpixel-Based Multi-Feature Graph Learning for Hyperspectral Image Data

Graphs naturally lend themselves to model the complexities of Hyperspectral Image (HSI) data as well as to serve as semi-supervised classifiers by propagating given labels among nearest neighbours. In this work, we present a novel framework for the classification of HSI data in light of a very limited amount of labelled data, inspired by multi-view graph learning and graph signal processing. Given an a priori superpixel-segmented hyperspectral image, we seek a robust and efficient graph construction and label propagation method to conduct semi-supervised learning (SSL). Since the graph is paramount to the success of the subsequent classification task, particularly in light of the intrinsic complexity of HSI data, we consider the problem of finding the optimal graph to model such data. Our contribution is two-fold: firstly, we propose a multi-stage edge-efficient semi-supervised graph learning framework for HSI data which exploits given label information through pseudo-label features embedded in the graph construction. Secondly, we examine and enhance the contribution of multiple superpixel features embedded in the graph on the basis of pseudo-labels in an extension of the previous framework, which is less reliant on excessive parameter tuning. Ultimately, we demonstrate the superiority of our approaches in comparison with state-of-the-art methods through extensive numerical experiments.

RLP-AGMC: Robust label propagation for saliency detection based on an adaptive graph with multiview connections

There have been remarkable improvements in the salient object detection in the recent years. During the past few years, graph-based saliency detection algorithms have been proposed and made advances. Nevertheless, most of the state-of-the-art graph-based approaches are usually designed with low-level features, misleading assumption, fixed predefined graph structure and weak affinity matrix, which determine that they are not robust enough to handle images with complex or cluttered background.In this paper, we propose a robust label propagation-based mechanism for salient object detection throughout an adaptive graph to tackle above issues. Low-level features as well as deep features are integrated into the proposed framework to measure the similarity between different nodes. In addition, a robust mechanism is presented to calculate seeds based on the distribution of salient regions, which can achieve desirable results even if the object is in contact with the image boundary and the image scene is complex. Then, an adaptive graph with multiview connections is constructed based on different cues to learn the graph affinity matrix, which can better capture the characteristics between spatially adjacent and distant regions. Finally, a novel RLP-AGMC model, i.e. robust label propagation throughout an adaptive graph with multiview connections, is put forward to calculate saliency maps in combination with the obtained seed vectors. Comprehensive experiments on six public datasets demonstrate the proposed method outperforms fourteen existing state-of-the-art methods in terms of various evaluation metrics.

Robust and sparse label propagation for graph-based semi-supervised classification

Robust and sparse label propagation for graph-based semi-supervised classification

Categorical Exploratory Data Analysis: From Multiclass Classification and Response Manifold Analytics Perspectives of Baseball Pitching Dynamics.

All features of any data type are universally equipped with categorical nature revealed through histograms. A contingency table framed by two histograms affords directional and mutual associations based on rescaled conditional Shannon entropies for any feature-pair. The heatmap of the mutual association matrix of all features becomes a roadmap showing which features are highly associative with which features. We develop our data analysis paradigm called categorical exploratory data analysis (CEDA) with this heatmap as a foundation. CEDA is demonstrated to provide new resolutions for two topics: multiclass classification (MCC) with one single categorical response variable and response manifold analytics (RMA) with multiple response variables. We compute visible and explainable information contents with multiscale and heterogeneous deterministic and stochastic structures in both topics. MCC involves all feature-group specific mixing geometries of labeled high-dimensional point-clouds. Upon each identified feature-group, we devise an indirect distance measure, a robust label embedding tree (LET), and a series of tree-based binary competitions to discover and present asymmetric mixing geometries. Then, a chain of complementary feature-groups offers a collection of mixing geometric pattern-categories with multiple perspective views. RMA studies a system’s regulating principles via multiple dimensional manifolds jointly constituted by targeted multiple response features and selected major covariate features. This manifold is marked with categorical localities reflecting major effects. Diverse minor effects are checked and identified across all localities for heterogeneity. Both MCC and RMA information contents are computed for data’s information content with predictive inferences as by-products. We illustrate CEDA developments via Iris data and demonstrate its applications on data taken from the PITCHf/x database.