Related papers: Neglected Free Lunch -- Learning Image Classifiers…
Natural Language Understanding (NLU) models are typically trained in a supervised learning framework. In the case of intent classification, the predicted labels are predefined and based on the designed annotation schema while the labelling…
State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…
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…
Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…
Many real-world applications involve data from multiple modalities and thus exhibit the view heterogeneity. For example, user modeling on social media might leverage both the topology of the underlying social network and the content of the…
Supervised object detection has been proven to be successful in many benchmark datasets achieving human-level performances. However, acquiring a large amount of labeled image samples for supervised detection training is tedious,…
Standard myopic active learning assumes that human annotations are always obtainable whenever new samples are selected. This, however, is unrealistic in many real-world applications where human experts are not readily available at all…
Many structured prediction problems (particularly in vision and language domains) are ambiguous, with multiple outputs being correct for an input - e.g. there are many ways of describing an image, multiple ways of translating a sentence;…
Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels…
Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality ground truth for training. Recent work has shown that prompt tuning of vision-language…
Deep metric learning (DML) based methods have been found very effective for content-based image retrieval (CBIR) in remote sensing (RS). For accurately learning the model parameters of deep neural networks, most of the DML methods require a…
Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,multiple annotations may be available. In either case,…
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process. However, traditional methods of human activity recognition require a large amount of such strictly labeled data for…
The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of…
Objects, in the real world, rarely occur in isolation and exhibit typical arrangements governed by their independent utility, and their expected interaction with humans and other objects in the context. For example, a chair is expected near…
In binary classification, Learning from Positive and Unlabeled data (LePU) is semi-supervised learning but with labeled elements from only one class. Most of the research on LePU relies on some form of independence between the selection…
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either…
Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques can be used to…
The number of social images has exploded by the wide adoption of social networks, and people like to share their comments about them. These comments can be a description of the image, or some objects, attributes, scenes in it, which are…
Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…