Automated supernova Ia classification using adaptive learning techniques

In this work, we propose the use of Kernel Principal Component Analysis (KPCA) combined with k = 1 nearest neighbour algorithm (1NN) as a framework for supernovae (SNe) photometric classification. The classification is entirely based on information within the spectroscopic confirmed sample and each new light curve is classified one at a time. This allows us to update the principal component (PC) parameter space if a new spectroscopic light curve is available while also avoids the need of re-determining it for each individual new classification. We applied the method to different instances of the \textit{Supernova Photometric Classification Challenge} (SNPCC) data set. Our method provide good purity results in all data sample analysed, when SNR$\geq$5. As a consequence, we can state that if a sample as the post-SNPCC was available today, we would be able to classify $\approx 15%$ of the initial data set with purity $\gtrsim$ 90% (D$_{7}$+SNR3). Results from the original SNPCC sample, reported as a function of redshift, show that our method provides high purity (up to $\approx 97%$), specially in the range of $0.2\leq z < 0.4$, when compared to results from the SNPCC, while maintaining a moderate figure of merit ($\approx 0.25$). We also present results for SNe photometric classification using only pre-maximum epochs, obtaining 63% purity and 77% successful classification rates (SNR$\geq$5). Results are sensitive to the information contained in each light curve, as a consequence, higher quality data points lead to higher successful classification rates. The method is flexible enough to be applied to other astrophysical transients, as long as a training and a test sample are provided.

Supernova (SN) classification and redshift estimation using photometric data only have become very important for the Large Synoptic Survey Telescope (LSST), given the large number of SNe that LSST will observe and the impossibility of spectroscopically following up all the SNe. We investigate the performance of a SN classifier that uses SN colors to classify LSST SNe with the Random Forest classification algorithm. Our classifier results in an AUC of 0.98 which represents excellent classification. We are able to obtain a photometric SN sample containing 99$\%$ SNe Ia by choosing a probability threshold. We estimate the photometric redshifts (photo-z) of SNe in our sample by fitting the SN light curves using the SALT2 model with nested sampling. We obtain a mean bias ($\left<z_\mathrm{phot}-z_\mathrm{spec}\right>$) of 0.012 with $\sigma\left( \frac{z_\mathrm{phot}-z_\mathrm{spec}}{1+z_\mathrm{spec}}\right) = 0.0294$ without using a host-galaxy photo-z prior, and a mean bias ($\left<z_\mathrm{phot}-z_\mathrm{spec}\right>$) of 0.0017 with $\sigma\left( \frac{z_\mathrm{phot}-z_\mathrm{spec}}{1+z_\mathrm{spec}}\right) = 0.0116$ using a host-galaxy photo-z prior. Assuming a flat $\Lambda CDM$ model with $\Omega_m=0.3$, we obtain $\Omega_m$ of $0.305\pm0.008$ (statistical errors only), using the simulated LSST sample of photometric SNe Ia (with intrinsic scatter $\sigma_\mathrm{int}=0.11$) derived using our methodology without using host-galaxy photo-z prior. Our method will help boost the power of SNe from the LSST as cosmological probes.

The efficient classification of different types of supernovae is one of the most important problems for observational cosmology. However, spectroscopic confirmation of most objects in upcoming photometric surveys, such as the the Rubin Observatory Legacy Survey of Space and Time, will be unfeasible. The development of automated classification processes based on photometry has thus become crucial. In this paper, we investigate the performance of machine learning (ML) classification on the final cosmological constraints using simulated light-curves from the Supernova Photometric Classification Challenge, released in 2010. We study the use of different feature sets for the light-curves and many different ML pipelines based on either decision-tree ensembles or automated search processes. To construct the final catalogues we propose a threshold selection method, by employing a bias-variance tradeoff. This is a very robust and efficient way to minimize the mean squared error. With this method, we were able to obtain very strong cosmological constraints, which allowed us to keep $\sim 75{{\ \rm per\ cent}}$ of the total information in the Type Ia supernovae when using the SALT2 feature set, and $\sim 33{{\ \rm per\ cent}}$ for the other cases (based either on the Newling model or on standard wavelet decomposition).

Supervised learning methods require sufficient labeled examples to learn a good model for classification or regression. However, available labeled data are insufficient in many applications. Active learning (AL) and domain adaptation (DA) are two strategies to minimize the required amount of labeled data for model training. AL requires the domain expert to label a small number of highly informative examples to facilitate classification, while DA involves tuning the source domain knowledge for classification on the target domain. In this paper, we demonstrate how AL can efficiently minimize the required amount of labeled data for DA. Since the source and target domains usually have different distributions, it is possible that the domain expert may not have sufficient knowledge to answer each query correctly. We exploit our active DA framework to handle incorrect labels provided by domain experts. Experiments with multimedia data demonstrate the efficiency of our proposed framework for active DA with noisy labels.

PurposeThe study aims to cope with the problems confronted in the skin lesion datasets with less training data toward the classification of melanoma. The vital, challenging issue is the insufficiency of training data that occurred while classifying the lesions as melanoma and non-melanoma.Design/methodology/approachIn this work, a transfer learning (TL) framework Transfer Constituent Support Vector Machine (TrCSVM) is designed for melanoma classification based on feature-based domain adaptation (FBDA) leveraging the support vector machine (SVM) and Transfer AdaBoost (TrAdaBoost). The working of the framework is twofold: at first, SVM is utilized for domain adaptation for learning much transferrable representation between source and target domain. In the first phase, for homogeneous domain adaptation, it augments features by transforming the data from source and target (different but related) domains in a shared-subspace. In the second phase, for heterogeneous domain adaptation, it leverages knowledge by augmenting features from source to target (different and not related) domains to a shared-subspace. Second, TrAdaBoost is utilized to adjust the weights of wrongly classified data in the newly generated source and target datasets.FindingsThe experimental results empirically prove the superiority of TrCSVM than the state-of-the-art TL methods on less-sized datasets with an accuracy of 98.82%.Originality/valueExperiments are conducted on six skin lesion datasets and performance is compared based on accuracy, precision, sensitivity, and specificity. The effectiveness of TrCSVM is evaluated on ten other datasets towards testing its generalizing behavior. Its performance is also compared with two existing TL frameworks (TrResampling, TrAdaBoost) for the classification of melanoma.

Dual contrastive universal adaptation network for multi-source visual recognition

When deep neural networks are deployed in a highly automated vehicle for environment perception tasks in an unseen (target) domain that differs from the training (source) domain, the mismatch will result in decreased performance. Domain adaptation methods aim at overcoming this mismatch. Many recently investigated methods for unsupervised domain adaptation train a model using labeled source data and unlabeled target data at the same time. These methods assume that data from the target domain is available during the source domain training, which is not always the case in real applications. In this paper we present a way to perform an online style transfer for continual domain adaptation which improves performance on (multiple) unseen target domains using a given perception model. The approach is based on an image style transfer in the frequency domain and requires neither an adjustment of the given source-trained model parameters to the target domain, nor does it require any considerable amount of memory for storing its frequency domain representation of the source domain style, which is particularly important considering the hardware limitations in an autonomous vehicle.

This paper addresses the problem of land-cover map updating by classification of multitemporal remote-sensing images in the context of domain adaptation (DA). The basic assumptions behind the proposed approach are twofold. The first one is that training data (ground reference information) are available for one of the considered multitemporal acquisitions (source domain) whereas they are not for the other (target domain). The second one is that multitemporal acquisitions (i.e., target and source domains) may be characterized by different sets of classes. Unlike other approaches available in the literature, the proposed DA Bayesian classifier based on maximum a posteriori decision rule (DA-MAP) automatically identifies whether there exist differences between the set of classes in the target and source domains and properly handles these differences in the updating process. The proposed method was tested in different scenarios of increasing complexity related to multitemporal image classification. Experimental results on medium-resolution and very high resolution multitemporal remote-sensing data sets confirm the effectiveness and the reliability of the proposed DA-MAP classifier.

In the absence of the labeled samples in a domain referred to as target domain, Domain Adaptation (DA) techniques come in handy. Generally, DA techniques assume there are available source domains that share similar predictive function with the target domain. Two core challenges of DA typically arise, variance that exists between source and target domains, and the inherent source hypothesis bias. In this paper, we first propose a Stability Transfer criterion for selecting relevant source domains with low variance. With this criterion, we introduce a TARget learning Assisted by Source Classifier Adaptation (TARASCA) method to address the two core challenges that have impeded the performances of DA techniques. To verify the robustness of TARASCA, extensive experimental studies are carried out with comparison to several state-of-the-art DA methods on the real-world Sentiment and Newsgroups datasets, where various settings for the class ratios of the source and target domains are considered.

Active multi-kernel domain adaptation for hyperspectral image classification

Domain adaptation is a key approach to ensure that artificial intelligence models maintain reliable performance when facing distributional shifts between training (source) and testing (target) domains. However, existing methods often struggle to simultaneously preserve domain-invariant representations and discriminative class structures, particularly in the presence of complex covariate shifts and noisy pseudo-labels in the target domain. In this work, we introduce Conditional Rényi α-Entropy Domain Adaptation, named CREDA, a novel deep learning framework for domain adaptation that integrates kernel-based conditional alignment with a differentiable, matrix-based formulation of Rényi’s quadratic entropy. The proposed method comprises three main components: (i) a deep feature extractor that learns domain-invariant representations from labeled source and unlabeled target data; (ii) an entropy-weighted approach that down-weights low-confidence pseudo-labels, enhancing stability in uncertain regions; and (iii) a class-conditional alignment loss, formulated as a Rényi-based entropy kernel estimator, that enforces semantic consistency in the latent space. We validate CREDA on standard benchmark datasets for image classification, including Digits, ImageCLEF-DA, and Office-31, showing competitive performance against both classical and deep learning-based approaches. Furthermore, we employ nonlinear dimensionality reduction and class activation maps visualizations to provide interpretability, revealing meaningful alignment in feature space and offering insights into the relevance of individual samples and attributes. Experimental results confirm that CREDA improves cross-domain generalization while promoting accuracy, robustness, and interpretability.

Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation. While some approaches to the problem require labelled data from the target domain, others adopt an unsupervised approach to domain adaptation (UDA). Evaluating UDA methods consists of measuring the model’s ability to generalise to unseen data in the target domain. In this work, we argue that this is not as useful as adapting to the test set directly. We therefore propose an evaluation framework where we perform test-time UDA on each subject separately. We show that models adapted to a specific target subject from the target domain outperform a domain adaptation method which has seen more data of the target domain but not this specific target subject. This result supports the thesis that unsupervised domain adaptation should be used at test-time, even if only using a single target-domain subject.

Sample-to-sample correspondence for unsupervised domain adaptation

Great progress has been achieved in domain adaptation in decades. Existing works are always based on an ideal assumption that testing target domains are independent and identically distributed with training target domains. However, due to unpredictable corruptions (e.g., noise and blur) in real data, such as web images and real-world object detection, domain adaptation methods are increasingly required to be corruption robust on target domains. We investigate a new task, corruption-agnostic robust domain adaptation (CRDA), to be accurate on original data and robust against unavailable-for-training corruptions on target domains. This task is non-trivial due to the large domain discrepancy and unsupervised target domains. We observe that simple combinations of popular methods of domain adaptation and corruption robustness have suboptimal CRDA results. We propose a new approach based on two technical insights into CRDA, as follows: (1) an easy-to-plug module called domain discrepancy generator (DDG) that generates samples that enlarge domain discrepancy to mimic unpredictable corruptions; (2) a simple but effective teacher-student scheme with contrastive loss to enhance the constraints on target domains. Experiments verify that DDG maintains or even improves its performance on original data and achieves better corruption robustness than baselines. Our code is available at: https://github.com/YifanXu74/CRDA .

Domain Adaptation (DA) methods are usually carried out by means of simply reducing the marginal distribution differences between the source and target domains, and subsequently using the resultant trained classifier, namely source classifier, for use in the target domain. However, in many cases, the true predictive distributions of the source and target domains can be vastly different especially when their class distributions are skewed, causing the issues of sample selection bias in DA. Hence, DA methods which leverage the source labeled data may suffer from poor generalization in the target domain, resulting in negative transfer. In addition, we observed that many DA methods use either a source classifier or a linear combination of source classifiers with a fixed weighting for predicting the target unlabeled data. Essentially, the labels of the target unlabeled data are spanned by the prediction of these source classifiers. Motivated by these observations, in this paper, we propose to construct many source classifiers of diverse biases and learn the weight for each source classifier by directly minimizing the structural risk defined on the target unlabeled data so as to heal the possible sample selection bias. Since the weights are learned by maximizing the margin of separation between opposite classes on the target unlabeled data, the proposed method is established here as Maximal Margin Target Label Learning (MMTLL), which is in a form of Multiple Kernel Learning problem with many label kernels. Extensive experimental studies of MMTLL against several state-of-the-art methods on the Sentiment and Newsgroups datasets with various imbalanced class settings showed that MMTLL exhibited robust accuracies on all the settings considered and was resilient to negative transfer, in contrast to other counterpart methods which suffered significantly in prediction accuracy.