Invariant Feature Space Research Articles

A unified framework for visual domain adaptation with covariance matching

In the field of Machine Learning, it is widely acknowledged that training and test data should ideally stem from the same source and distribution. However, in the real world, this is not always feasible. Domain Adaptation (DA) techniques address this issue by adapting a classifier trained on annotated source domain data on unannotated target domain data while minimizing the impact of domain shift. Many recent DA approaches concentrate on learning a latent feature space that remains invariant to domain shift by mitigating various statistical and geometrical divergences. Although these methods have demonstrated effectiveness, they frequently overlook a crucial aspect of learning a domain-invariant discriminative latent feature space across diverse domains. To address this issue, we propose a novel framework called Unified Framework for Visual Domain Adaptation with Covariance Matching (UDACM) that aims to learn a domain invariant and class discriminative latent feature space by incorporating multiple objectives such as maximizing target domain variance, minimizing distribution and subspace divergence, performing manifold learning, preserving discriminative information of both the source and target domains, and measuring and matching covariance simultaneously. In our proposed framework, the measuring and matching of covariance play a crucial role in ensuring the learning of discriminative latent feature space by aligning the within-class and between-class covariance matrices of the source and target domains simultaneously. Detailed experiments demonstrate the outperformance of UDACM on baseline datasets such as CMU-PIE, Office+Caltech10, USPS+MNIST, VLCS, and Office–Home, compared to various established primitive, shallow, and deep domain adaptation methods on several image classification tasks.

Toward a robust detection of viscous and turbulent flow regions using unsupervised machine learning

We propose an invariant feature space for the detection of viscous-dominated and turbulent regions (i.e., boundary layers and wakes). The developed methodology uses the principal invariants of the strain and rotational rate tensors as input to an unsupervised Machine Learning Gaussian mixture model. The selected feature space is independent of the coordinate frame used to generate the processed data, as it relies on the principal invariants of the strain and rotational rate, which are Galilean invariants. This methodology allows us to identify two distinct flow regions: a viscous-dominated, rotational region (a boundary layer and a wake region) and an inviscid, irrotational region (an outer flow region). We have tested the methodology on a laminar and a turbulent (using Large Eddy Simulation) case for flows past a circular cylinder at Re = 40 and Re = 3900 and a laminar flow around an airfoil at Re=1×105. The simulations have been conducted using a high-order nodal Discontinuous Galerkin Spectral Element Method. The results obtained are analyzed to show that Gaussian mixture clustering provides an effective identification method of viscous-dominated and rotational regions in the flow. We also include comparisons with traditional sensors to show that the proposed clustering does not depend on the selection of an arbitrary threshold, as required when using traditional sensors.

Adaptive Domain Generalization Via Online Disagreement Minimization.

Deep neural networks suffer from significant performance deterioration when there exists distribution shift between deployment and training. Domain Generalization (DG) aims to safely transfer a model to unseen target domains by only relying on a set of source domains. Although various DG approaches have been proposed, a recent study named DomainBed (Gulrajani and Lopez-Paz, 2020), reveals that most of them do not beat simple empirical risk minimization (ERM). To this end, we propose a general framework that is orthogonal to existing DG algorithms and could improve their performance consistently. Unlike previous DG works that stake on a static source model to be hopefully a universal one, our proposed AdaODM adaptively modifies the source model at test time for different target domains. Specifically, we create multiple domain-specific classifiers upon a shared domain-generic feature extractor. The feature extractor and classifiers are trained in an adversarial way, where the feature extractor embeds the input samples into a domain-invariant space, and the multiple classifiers capture the distinct decision boundaries that each of them relates to a specific source domain. During testing, distribution differences between target and source domains could be effectively measured by leveraging prediction disagreement among source classifiers. By fine-tuning source models to minimize the disagreement at test time, target-domain features are well aligned to the invariant feature space. We verify AdaODM on two popular DG methods, namely ERM and CORAL, and four DG benchmarks, namely VLCS, PACS, OfficeHome, and TerraIncognita. The results show AdaODM stably improves the generalization capacity on unseen domains and achieves state-of-the-art performance.

Robust image hashing for content identification through contrastive self-supervised learning

Content identification systems are an essential technology for many applications. These systems identify query multimedia items using a database of known identities. A hash-based system uses a perceptual hashing function that generates a hash value invariant against a set of expected manipulations in an image, later compared to perform identification. Usually, this set of manipulations is well-known, and the researcher creates the perceptual hashing function that best adapts to the set. However, a new manipulation may break the hashing function, requiring to create a new one, which may be costly and time-consuming. Therefore, we propose to let the hashing function learn an invariant feature space automatically. For this, we exploit the recent advances in self-supervised learning, where a model uses unlabeled data to generate a feature representation by solving a metric learning-based pretext task that enforces the robust image hashing properties for content identification systems. To achieve model transferability on unseen data, our pretext task enforces the feature vector invariance against the manipulation set, and through random sampling on the unlabeled training set, we present the model a wide variety of perceptual information to work on. As exhaustive experimentation shows, this method achieves excellent robustness against a comprehensive set of manipulations, even difficult ones such as horizontal flip and rotation, with excellent identification performance. Also, the trained model is highly discriminative against the presence of near-duplicate images. Furthermore, this method does not need re-training or fine-tuning on a new dataset to achieve the observed performance, indicating an excellent generalization capacity.

Pivot-Guided Embedding for Domain Generalization

Neural networks have suffered from a distribution gap between training and test data, known as domain shift. Domain generalization (DG) methods aim to learn domain invariant representations only with limited source domain data to cope with unseen target domains. The main assumption is that the model trained to extract semantically consistent features without any domain specific information is highly adaptable to the unseen target domain. Metric learning allows embedding representations to be class-separated and domain-mixed, which is an optimal condition for DG but has been downplayed in recent works. Even the most popular triplet embedding has limitations in forming an optimal embedding space for DG due to instability. In this paper, we present a novel deep metric learning method for domain invariant representations. Specifically, we propose Pivot-Guided Embedding (PGE), which explicitly forms the entire feature distribution of the embedding space with a novel pivot-guided attraction-repulsion mechanism, to address the instability problem that triplet embedding has. In particular, we leverage pivot features representing a coarse distribution of the entire space as reference points to guide other features toward domain invariant feature distribution. To this end, a pivot selection algorithm is presented to reliably reflect the entire feature distribution. Furthermore, we define Guide-Field, a subspace spanned by a subset of pivots chosen for individual samples, to guide each sample to domain invariant feature space. In a nutshell, the attraction-repulsion mechanism based on pivots, the reliable set of features representing the entire feature distribution, enables the model to extract domain invariant feature representations and also settles the instability problem of triplet loss. Experimental results on three different benchmarks validate the performance advantages of the proposed method over the state-of-the-art DG techniques.

A Meta-Invariant Feature Space Method for Accurate Tool Wear Prediction Under Cross Conditions

Cross conditions prediction is a prevalent problem in manufacturing area, where tool wear prediction is a typical one. Existing data-driven methods for tool wear prediction mainly focus on cutting conditions with small variations, which encounters much difficulty under cross conditions with large variations, and the essential is the difference of both marginal distribution and conditional distribution of the data under cross conditions. To address this issue, this article proposes a meta-invariant feature space (MIFS) learning method, where invariant feature space is constructed for paired tasks to close marginal distribution, whose nature law under cross conditions is learned by meta-learning, i.e., MIFS, which can be adapted to achieve accurate tool wear prediction under cross conditions with a small number of new samples. Experimental results provided positive confirmation on the feasibility and accuracy of the proposed method, which can also be readily extended to regression and classification problems in other fields.

Discriminative active learning for domain adaptation

Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous works mainly focused on matching the marginal feature distributions using the adversarial training methods while assuming the conditional relations between the source and target domain remained unchanged, i.e., ignoring the conditional shift problem. However, recent works have shown that such a conditional shift problem exists and can hinder the adaptation process. To address this issue, we have to leverage labeled data from the target domain, but collecting labeled data can be quite expensive and time-consuming. To this end, we introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation. Specifically, we propose three-stage active adversarial training of neural networks: invariant feature space learning (first stage), uncertainty and diversity criteria and their trade-off for query strategy (second stage) and re-training with queried target labels (third stage). Empirical comparisons with existing domain adaptation methods using four benchmark datasets demonstrate the effectiveness of the proposed approach. Furthermore, by comparing different query strategies, we could demonstrate the benefits of our proposed method.

Deep Representation-Based Domain Adaptation for Nonstationary EEG Classification.

In the context of motor imagery, electroencephalography (EEG) data vary from subject to subject such that the performance of a classifier trained on data of multiple subjects from a specific domain typically degrades when applied to a different subject. While collecting enough samples from each subject would address this issue, it is often too time-consuming and impractical. To tackle this problem, we propose a novel end-to-end deep domain adaptation method to improve the classification performance on a single subject (target domain) by taking the useful information from multiple subjects (source domain) into consideration. Especially, the proposed method jointly optimizes three modules, including a feature extractor, a classifier, and a domain discriminator. The feature extractor learns the discriminative latent features by mapping the raw EEG signals into a deep representation space. A center loss is further employed to constrain an invariant feature space and reduce the intrasubject nonstationarity. Furthermore, the domain discriminator matches the feature distribution shift between source and target domains by an adversarial learning strategy. Finally, based on the consistent deep features from both domains, the classifier is able to leverage the information from the source domain and accurately predict the label in the target domain at the test time. To evaluate our method, we have conducted extensive experiments on two real public EEG data sets, data set IIa, and data set IIb of brain-computer interface (BCI) Competition IV. The experimental results validate the efficacy of our method. Therefore, our method is promising to reduce the calibration time for the use of BCI and promote the development of BCI.

Unsupervised Domain Adaptation for Classification of Histopathology Whole-Slide Images.

Computational image analysis is one means for evaluating digitized histopathology specimens that can increase the reproducibility and reliability with which cancer diagnoses are rendered while simultaneously providing insight as to the underlying mechanisms of disease onset and progression. A major challenge that is confronted when analyzing samples that have been prepared at disparate laboratories and institutions is that the algorithms used to assess the digitized specimens often exhibit heterogeneous staining characteristics because of slight differences in incubation times and the protocols used to prepare the samples. Unfortunately, such variations can render a prediction model learned from one batch of specimens ineffective for characterizing an ensemble originating from another site. In this work, we propose to adopt unsupervised domain adaptation to effectively transfer the discriminative knowledge obtained from any given source domain to the target domain without requiring any additional labeling or annotation of images at the target site. In this paper, our team investigates the use of two approaches for performing the adaptation: (1) color normalization and (2) adversarial training. The adversarial training strategy is implemented through the use of convolutional neural networks to find an invariant feature space and Siamese architecture within the target domain to add a regularization that is appropriate for the entire set of whole-slide images. The adversarial adaptation results in significant classification improvement compared with the baseline models under a wide range of experimental settings.

An effective image retrieval framework in invariant feature space merging GeoSOM with modified inverted indexing

The complexity in retrieving diverse images with different affine transformations poses a challenging issue to researchers. Hence, this paper offers one such framework targeting the aforesaid concern. Accordingly, a three step retrieval framework is proposed that initially extracts Invariant Zernike Moment Descriptor (IZMD) features from the query database. The attained features are then vector quantized by the Geodesic Self-Organizing Map (GeoSOM) to produce the feature codebook. Finally, a slight variant of the inverted indexing scheme operates on the GeoSOM codebook to produce the closely related images. This enforces a weighting and matching strategy that reduces the search space and time. Simulation analysis of the presented framework is performed on color and medical datasets using the standard evaluation measures. Relative analysis with the state-of-the-art schemes show betterment in terms of Precision-Recall (P-R) and other performance parameters.

Transferring Subspaces Between Subjects in Brain--Computer Interfacing

Compensating changes between a subjects' training and testing session in brain-computer interfacing (BCI) is challenging but of great importance for a robust BCI operation. We show that such changes are very similar between subjects, and thus can be reliably estimated using data from other users and utilized to construct an invariant feature space. This novel approach to learning from other subjects aims to reduce the adverse effects of common nonstationarities, but does not transfer discriminative information. This is an important conceptual difference to standard multisubject methods that, e.g., improve the covariance matrix estimation by shrinking it toward the average of other users or construct a global feature space. These methods do not reduces the shift between training and test data and may produce poor results when subjects have very different signal characteristics. In this paper, we compare our approach to two state-of-the-art multisubject methods on toy data and two datasets of EEG recordings from subjects performing motor imagery. We show that it can not only achieve a significant increase in performance, but also that the extracted change patterns allow for a neurophysiologically meaningful interpretation.

Classification of silhouettes using contour fragments

In this paper, we propose a fragment-based approach for classification and recognition of shape contours. According to this method, first the perceptual landmarks along the contours are localized in a scale invariant manner, which makes it possible to extracts the contour fragments. Using a predefined dictionary for the fragments, these landmarks and the parts between them are transformed into a symbolic representation that is a compact representation. Using a string kernel-like approach, an invariant high-dimensional feature space is created from the symbolic representation and later the most relevant lower dimensions are extracted by principal component analysis. Finally, support vector machine is used for classification of the feature space. The experimental results show that the proposed method has similar performance to the best approaches for shape recognitions while it has lower complexity.

Radon Representation-Based Feature Descriptor for Texture Classification

In this paper, we aim to handle the intraclass variation resulting from the geometric transformation and the illumination change for more robust texture classification. To this end, we propose a novel feature descriptor called Radon representation-based feature descriptor (RRFD). RRFD converts the original pixel represented images into Radon-pixel images by using the Radon transform. The new Radon-pixel representation is more informative in geometry and has a much lower dimension. Subsequently, RRFD efficiently achieves affine invariance by projecting an image (or an image patch) from the space of Radon-pixel pairs onto an invariant feature space by using a ratiogram, i.e., the histogram of ratios between the areas of triangle pairs. The illumination invariance is also achieved by defining an illumination invariant distance metric on the invariant feature space. Comparing to the existing Radon transform-based texture features, which only achieve rotation and/or scaling invariance, RRFD achieves affine invariance. The experimental results on CUReT show that RRFD is a powerful feature descriptor that is suitable for texture classification.

Affine invariant comparison of point-sets using convex hulls and hausdorff distances

Many object recognition or identification applications involve comparing features associated with point-sets. This paper presents an affine invariant point-set matching technique which measures the similarity between two point-sets by embedding them into an affine invariant feature space. The developed technique assumes no a priori knowledge of reference points, as is the case in many identification problems. Reference points of a point-set are obtained based on its convex hull. An enhanced version of the Modified Hausdorff Distance is also introduced and used in the feature space for comparing two point-sets. It should be noted that the technique does not attempt to obtain correspondences between the point-sets. The introduced technique is applied to two real databases and its performance is found favorable as compared to three other affine invariant matching techniques.

상대거리-곡률 특징 공간을 이용한 형태 기술 및 인식

영상에 회전이나 크기 변형이 가해지면 영상을 구성하는 점들의 좌표값들이 변경되어 형태 기술 및 인식이 어렵게 된다. 그러나 영상을 구성하는 점들 간의 위치관계나 무게중심과의 위치 관계는 변하지 않는다. 따라서 x-y 좌표계로 기술되는 영상 공간의 점들을 회전 및 크기 변형에 불변하는 새로운 좌표계로 사상할 수 있다면, 형태 기술 및 인식의 문제는 보다 수월해진다. 본 논문에서는 영상 공간의 점들을 회전 및 크기 변형에 무관한 새로운 특징 공간으로 사상하여 형태를 기술하는 방법을 제안한다. 특징 공간을 나타내는 새로운 좌표계는 무게중심으로부터의 상대거리와 윤곽선 세그먼트 곡률을 두 축으로 하는 직교 좌표계이다. 상대거리는 윤곽선 상의 임의의 한 점이 무게중심에서 얼마나 멀리 벗어나 있는지를 나타내는 값이고, 윤곽선 세그먼트 곡률은 세그먼트의 굴곡도를 나타내는 값이다. 특징 공간에 사상된 점들의 형태 기술은 메쉬 특징을 통해 이루어진다. 실험을 통해 제안된 형태 기술 방법이 회전 및 크기 변형에 강건함을 확인하였다. Rotation and scale variations make it difficult to solve the problem of shape description and recognition because these variations change the location of points composing the shape. However, some geometric Invariant points and the relations among them are not changed by these variations. Therefore, if points in image space depicted with the r-y coordinates system can be transformed into a new coordinates system that are invariant to rotation and scale, the problem of shape description and recognition becomes easier. This paper presents a shape description method via transformation from the image space into the invariant feature space having two axes: representing relative distance from a centroid and contour segment curvature(CSC). The relative distance describes how far a point departs from the centroid, and the CSC represents the degree of fluctuation in a contour segment. After transformation, mesh features were used to describe the shape mapped onto the feature space. Experimental results show that the proposed method is robust to rotation and scale variations.