Semi-supervised distance metric learning for person re-identification

Person reidentification has attracted extensive research efforts in recent years. It is challenging due to the varied visual appearance from illumination, view angle, background, and possible occlusions, leading to the difficulties when measuring the relevance, i.e., similarities, between probe and gallery images. Existing methods mainly focus on pairwise distance metric learning for person reidentification. In practice, pairwise image matching may limit the data for comparison (just the probe and one gallery subject) and yet lead to suboptimal results. The correlation among gallery data can be also helpful for the person reidentification task. In this paper, we propose to investigate the high-order correlation among the probe and gallery data, not the pairwise matching, to jointly learn the relevance of gallery data to the probe. Recalling recent progresses on feature representation in person reidentification, it is difficult to select the best feature and each type of feature can benefit person description from different aspects. Under such circumstances, we propose a multihypergraph joint learning algorithm to learn the relevance in corporation with multiple features of the imaging data. More specifically, one hypergraph is constructed using one type of feature and multiple hypergraphs can be generated accordingly. Then, the learning process is conducted on the multihypergraph structure, and the identity of a probe is determined by its relevance to each gallery data. The merit of the proposed scheme is twofold. First, different from pairwise image matching, the proposed method jointly explores the relationships among different images. Second, multimodal data, i.e., different features, can be formulated in the multihypergraph structure, which can convey more information in the learning process and can be easily extended. We note that the proposed method is a general framework to incorporate with any combination of features, and thus is flexible in practice. Experimental results and comparisons with the state-of-the-art methods on three public benchmarking data sets demonstrate the superiority of the proposed method.

In this paper, we propose a new Multi-kernel Metric Learning (MKML) approach to enhance the performance of person re-identification using adaptive weighted Multi-kernel. The intuition behind our approach is that different features, i.e., low-level and middle-level features, have different nature and thus discriminating capability, utilizing different kernels could map these features into sub-spaces, which helps to improve the discrimination among features. The kernels are combined with an adaptive weighting strategy to get an efficient kernel space. The Fisher Discriminant Analysis (FDA) is used to learn the metric in the learned weighted kernels space that enhances the robustness of metric to discriminate among classes. Experiments on two challenging person reidentification datasets, i.e., VIPeR and CUHK01, demonstrated that our approach is effective.

Person re-identification problem is a valuable computer vision task, which aims at matching pedestrian images of different cameras in a non-overlapping surveillance network. Existing metric learning based methods address this problem by learning a robust distance function. These methods learn a mapping subspace by forcing the distance of the positive pair much smaller than the negative pair by a strict constraint. The metric model is over-fitting to the training dataset. Due to drastic appearance variations, the handcrafted features are weak of representation for person re-identification. To address these problems, we propose a joint distance measure based approach, which learns a Mahalanobis distance and a Euclidean distance with a novel feature jointly. The novel feature is represented with a dictionary representation based method which considers pedestrian images of different camera views with the same dictionary. The joint distance combine the Mahalanobis distance based on metric learning method with the Euclidean distance based on the novel feature to measure the similarity between matching pairs. Extensive experiments are conducted on the publicly available bench marking datasets VIPeR and CUHK01. The identification results show that the proposed method reaches a good performance than the comparison methods.

Machine Learning is a modern and actively developing field of computer science, devoted to extracting and estimating dependencies from empirical data. It combines such fields as statistics, optimization theory and artificial intelligence. In practical tasks, the general aim of Machine Learning is to construct algorithms able to generalize and predict in previously unseen situations based on some set of examples. Given some finite information, Machine Learning provides ways to exract knowledge, describe, explain and predict from data. Kernel Methods are one of the most successful branches of Machine Learning. They allow applying linear algorithms with well-founded properties such as generalization ability, to non-linear real-life problems. Support Vector Machine is a well-known example of a kernel method, which has found a wide range of applications in data analysis nowadays. In many practical applications, some additional prior knowledge is often available. This can be the knowledge about the data domain, invariant transformations, inner geometrical structures in data, some properties of the underlying process, etc. If used smartly, this information can provide significant improvement to any data processing algorithm. Thus, it is important to develop methods for incorporating prior knowledge into data-dependent models. The main objective of this thesis is to investigate approaches towards learning with kernel methods using prior knowledge. Invariant learning with kernel methods is considered in more details. In the first part of the thesis, kernels are developed which incorporate prior knowledge on invariant transformations. They apply when the desired transformation produce an object around every example, assuming that all points in the given object share the same class. Different types of objects, including hard geometrical objects and distributions are considered. These kernels were then applied for images classification with Support Vector Machines. Next, algorithms which specifically include prior knowledge are considered. An algorithm which linearly classifies distributions by their domain was developed. It is constructed such that it allows to apply kernels to solve non-linear tasks. Thus, it combines the discriminative power of support vector machines and the well-developed framework of generative models. It can be applied to a number of real-life tasks which include data represented as distributions. In the last part of the thesis, the use of unlabelled data as a source of prior knowledge is considered. The technique of modelling the unlabelled data with a graph is taken as a baseline from semi-supervised manifold learning. For classification problems, we use this apporach for building graph models of invariant manifolds. For regression problems, we use unlabelled data to take into account the inner geometry of the input space. To conclude, in this thesis we developed a number of approaches for incorporating some prior knowledge into kernel methods. We proposed invariant kernels for existing algorithms, developed new algorithms and adapted a technique taken from semi-supervised learning for invariant learning. In all these cases, links with related state-of-the-art approaches were investigated. Several illustrative experiments were carried out on real data on optical character recognition, face image classification, brain-computer interfaces, and a number of benchmark and synthetic datasets.

This paper investigates the use of semi-supervised learning (SSL) for predicting Alzheimers Disease (AD) conversion in Mild Cognitive Impairment (MCI) patients based on Magnetic Resonance Imaging (MRI). SSL methods differ from standard supervised learning methods in that they make use of unlabeled data - in this case data from MCI subjects whose final diagnosis is not yet known. We compare two widely used semi-supervised methods (low density separation (LDS) and semi-supervised discriminant analysis (SDA)) to the corresponding supervised methods using real and synthetic MRI data of MCI subjects. With simulated data, using SSL instead of supervised learning led to higher classification performance in certain cases, however, the applicability of semi-supervised methods depended strongly on the data distributions. With real MRI data, the SSL methods achieved significantly better classification performances over supervised methods. Moreover, even using a small number of unlabeled samples improved the AD conversion predictions.

Towards fast and kernelized orthogonal discriminant analysis on person re-identification

Semi-supervised medical image segmentation via a tripled-uncertainty guided mean teacher model with contrastive learning.

In principal component regression (PCR) and partial least‐squares regression (PLSR), the use of unlabeled data, in addition to labeled data, helps stabilize the latent subspaces in the calibration step, typically leading to a lower prediction error. For using unlabeled data in PLSR, a non‐sequential approach based on optimal filtering (OF) has been proposed in the literature. In this work, a sequential version of the OF‐based PLSR and a PCA‐based PLSR (PLSR applied to PCA‐preprocessed data) are proposed. It is shown analytically that the sequential version of the OF‐based PLSR is equivalent to that of PCA‐based PLSR, which leads to a new interpretation of OF. Simulated and experimental data sets are used to point out the usefulness and pitfalls of using unlabeled data. Unlabeled data can replace labeled data to some extent, thereby leading to an economic benefit. However, in the presence of drift, the use of unlabeled data can result in an increase in prediction error compared to that obtained with a model based on labeled data alone. Copyright © 2011 John Wiley & Sons, Ltd.

Nowadays deep learning is a tool, which is used in many different pattern recognition problems. For achieving strong results, which are reported in literature, often large amounts of data are necessary. In many use cases collecting or labeling data is very difficult or not possible at all. The aim of this paper is to compare three different algorithmic approaches in order to deal with limited access to labeled and unlabeled data. The drawbacks and benefits of each method are shown and compared to each other. A successful algorithmic approach, which is especially successful for one- and few-shot learning problems, is the usage of external data during the classification task. In this paper siamese neural networks will be investigated in order to evaluate how the usage of external data improves the accuracy. Another widely used approach is consistency regularization. Using consistency regularization state of the art results in semi-supervised learning (SSL) benchmarks are achieved. Virtual adversarial training (VAT) has shown strong results and is chosen as a representative algorithm for consistency regularization. The last approach is the usage of generative adversarial networks (GANs). In literature GANs are often used in order to create additional data and therefor to increase the generalization capability of the classification network. Furthermore the usage of unlabeled data for further performance improvement is considered. The use of unlabeled data is investigated for GANs and VAT.

Person re-identification is an important task of matching pedestrians across non-overlapping camera views. In this paper, we exploit a weighted feature descriptor for person re-identification. We firstly compute the weights on the superpixel level via graph-based manifold ranking algorithm, then integrate the computed weights into a patch-based feature descriptor, named local maximal occurrence. Finally, the weighted descriptors are fed into a top-push distance learning to mitigate the cross-view gaps. We evaluate the proposed method on three benchmark datasets iLIDS-VID, PRID 450S and VIPeR. The promising experimental results demonstrate the effectiveness of the proposed method comparing with the state-of-the-arts.

A hybrid Transformer-CNN framework for uncertainty-guided semi-supervised multiclass eye disease classification with enhanced interpretability.

This paper presents a novel semi-supervised end-to-end automatic speech recognition (ASR) method that employs consistency training with the use of unlabeled data. In consistency training, unlabeled data can be utilized for constraining a model such that it becomes invariant to small deformation. In fact, considering consistency can make the model robust to a variety of input examples. While previous studies have applied consistency training to primitive classification problems, no studies have employed consistency training to tackle sequence-to-sequence generation problems including end-to- end ASR. One problem is that existing consistency training schemes cannot take sequence-level generation consistency into consideration. In this paper, we propose a sequence-level consistency training scheme specialized to handle sequence-to-sequence generation problems. Our key idea is to consider the consistency of the generation function by utilizing beam search decoding results. For semi- supervised learning, we adopt Transformer as the end-to-end ASR model, and SpecAugment as the deformation function in consistency training. Our experiments show that our semi-supervised learning proposal with sequence-level consistency training can efficiently improve ASR performance using unlabeled speech data.

A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for building fair models with sacrifice in accuracy, most are geared toward either supervised or unsupervised learning. Yet two observations inspired us to wonder whether semi-supervised learning might be useful to solve discrimination problems. First, previous study showed that increasing the size of the training set may lead to a better trade-off between fairness and accuracy. Second, the most powerful models today require an enormous of data to train which, in practical terms, is likely possible from a combination of labeled and unlabeled data. Hence, in this paper, we present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data, a re-sampling method to obtain multiple fair datasets and lastly, ensemble learning to improve accuracy and decrease discrimination. A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning. A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.

Two-phase self-supervised pretraining for object re-identification

Gathering labeled data is one of the most time-consuming and expensive tasks in supervised machine learning. In practical applications, there are usually quite limited labeled training samples but abundant unlabeled data that is easy to collect. Semi-supervised learning and active learning are two important techniques for learning a discriminative classification model when labeled data is scarce. However, unlabeled data with significant noises and outliers cannot be well exploited and usually worsen the performance of semi-supervised learning and the performance of active learning also needs a powerful initial classifier learned from the quite limited labeled training data. In order to solve the above issues, in this paper we proposed a novel model of semi-supervised dictionary active learning (SSDAL), which aims to integrate semi-supervised learning and active learning to effectively use all the training data. In particular, two criterions based on estimated class possibility are designed to select the unlabeled data with confident class estimation for semi-supervised learning and the informative unlabeled data for active learning, respectively. Extensive experiments are conducted to show the superior performance of our method in classification applications, e.g., handwritten digit recognition, face recognition and large-scale image classification.