Related papers: Tight Lower Bounds on Worst-Case Guarantees for Ze…

Zero-shot recognition (ZSR) aims to recognize target-domain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative…

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become too expensive. Zero-shot learning requires an annotated set…

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper,…

Methods for object detection and segmentation often require abundant instance-level annotations for training, which are time-consuming and expensive to collect. To address this, the task of zero-shot object detection (or segmentation) aims…

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…

Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data. Traditional fully supervised…

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which…

Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute.…

Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…

Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the…

With recent progress in large-scale map maintenance and long-term map learning, the task of change detection on a large-scale map from a visual image captured by a mobile robot has become a problem of increasing criticality. Previous…

The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous…

While progress has been made in understanding the robustness of machine learning classifiers to test-time adversaries (evasion attacks), fundamental questions remain unresolved. In this paper, we use optimal transport to characterize the…

Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain. Recently, methods using generative models to combat…

Zero-shot learning (ZSL) aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. A recent paradigm called transductive zero-shot learning further leverages…

Zero-shot learning provides models for targets for which instances are not available, commonly called unobserved targets. The availability of target side information becomes crucial in this context in order to properly induce models for…

Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the error on future data (test error), for which the training…

Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating…

Many recent few-shot learning methods concentrate on designing novel model architectures. In this paper, we instead show that with a simple backbone convolutional network we can even surpass state-of-the-art classification accuracy. The…

Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for…