Related papers: Joint Discriminative and Metric Embedding Learning…

Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

In this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of…

Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

Classical person re-identification approaches assume that a person of interest has appeared across different cameras and can be queried by one of the existing images. However, in real-world surveillance scenarios, frequently no visual…

End-to-end speaker verification systems have received increasing interests. The traditional i-vector approach trains a generative model (basically a factor-analysis model) to extract i-vectors as speaker embeddings. In contrast, the…

Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function…

Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature…

The ability to correctly classify and retrieve apparel images has a variety of applications important to e-commerce, online advertising and internet search. In this work, we propose a robust framework for fine-grained apparel…

Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing…

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…

In the context of pose-invariant object recognition and retrieval, we demonstrate that it is possible to achieve significant improvements in performance if both the category-based and the object-identity-based embeddings are learned…

Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited…

While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy.…

Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the…

Most existing person re-identification (re-id) methods focus on learning the optimal distance metrics across camera views. Typically a person's appearance is represented using features of thousands of dimensions, whilst only hundreds of…

Improving the classification of multi-class imbalanced data is more difficult than its two-class counterpart. In this paper, we use deep neural networks to train new representations of tabular multi-class data. Unlike the typically…

Feature learning is a widely used method employed for large-scale face recognition. Recently, large-margin softmax loss methods have demonstrated significant enhancements on deep face recognition. These methods propose fixed positive…

This paper presents an approach to tackle the re-identification problem. This is a challenging problem due to the large variation of pose, illumination or camera view. More and more datasets are available to train machine learning models…

Image features for retrieval-based localization must be invariant to dynamic objects (e.g. cars) as well as seasonal and daytime changes. Such invariances are, up to some extent, learnable with existing methods using triplet-like losses,…