Related papers: Learning Discriminative Representations for Multi-…
Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption…
Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…
Visual object tracking remains an active research field in computer vision due to persisting challenges with various problem-specific factors in real-world scenes. Many existing tracking methods based on discriminative correlation filters…
Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse labels. As challenging as this…
We propose a novel pooling strategy that learns how to adaptively rank deep convolutional features for selecting more informative representations. To this end, we exploit discriminative analysis to project the features onto a space spanned…
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have…
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative…
Modern convolutional neural networks (CNNs) are able to achieve human-level object classification accuracy on specific tasks, and currently outperform competing models in explaining complex human visual representations. However, the…
Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinations. However, we…
Multi-label image classification is the task of predicting a set of labels corresponding to objects, attributes or other entities present in an image. In this work we propose the Classification Transformer (C-Tran), a general framework for…
Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for…
Many tasks in computer vision can be cast as a "label changing" problem, where the goal is to make a semantic change to the appearance of an image or some subject in an image in order to alter the class membership. Although successful…
Active deep learning classification of hyperspectral images is considered in this paper. Deep learning has achieved success in many applications, but good-quality labeled samples are needed to construct a deep learning network. It is…
We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality…
In classic video action recognition, labels may not contain enough information about the diverse video appearance and dynamics, thus, existing models that are trained under the standard supervised learning paradigm may extract less…
Multi-view multi-label classification (MvMLC) has recently garnered significant research attention due to its wide range of real-world applications. However, incompleteness in views and labels is a common challenge, often resulting from…
It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstream task. Recently, both supervised and unsupervised…
Knowledge representation of graph-based systems is fundamental across many disciplines. To date, most existing methods for representation learning primarily focus on networks with simplex labels, yet real-world objects (nodes) are…
In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures…
Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation…