Related papers: Selective Zero-Shot Classification with Augmented …

This paper proposes a novel non-intrusive system failure prediction technique using available information from developers and minimal information from raw logs (rather than mining entire logs) but keeping the data entirely private with the…

Video recognition models are typically trained on fixed taxonomies which are often too coarse, collapsing distinctions in object, manner or outcome under a single label. As tasks and definitions evolve, such models cannot accommodate…

Classification based on Zero-shot Learning (ZSL) is the ability of a model to classify inputs into novel classes on which the model has not previously seen any training examples. Providing an auxiliary descriptor in the form of a set of…

Due to the importance of zero-shot learning, the number of proposed approaches has increased steadily recently. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is three-fold.…

Classification systems are often deployed in resource-constrained settings where labels must be assigned to inputs on a budget of time, memory, etc. Budgeted, sequential classifiers (BSCs) address these scenarios by processing inputs…

This paper presents a simple yet effective method for improving the performance of zero-shot learning (ZSL). ZSL classifies instances of unseen classes, from which no training data is available, by utilizing the attributes of the classes.…

In selective classification (SC), a classifier abstains from making predictions that are likely to be wrong to avoid excessive errors. To deploy imperfect classifiers -- either due to intrinsic statistical noise of data or for robustness…

Zero-shot learning enables the model to recognize unseen categories with the aid of auxiliary semantic information such as attributes. Current works proposed to detect attributes from local image regions and align extracted features with…

Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing. A number of recently proposed approaches utilize a fully supervised object recognition model within…

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…

Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training. Despite the significant progress achieved by generative…

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…

Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for…

Machine learning plays an increasingly significant role in many aspects of our lives (including medicine, transportation, security, justice and other domains), making the potential consequences of false predictions increasingly devastating.…

Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. These predictions can then be deferred to humans for further evaluation. As an everlasting challenge for machine learning, in many…

Checklists are simple decision aids that are often used to promote safety and reliability in clinical applications. In this paper, we present a method to learn checklists for clinical decision support. We represent predictive checklists as…

Zero-shot learning (ZSL) aims to recognize a set of unseen classes without any training images. The standard approach to ZSL requires a set of training images annotated with seen class labels and a semantic descriptor for seen/unseen…

Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but are designed for general visual understanding, not…

Many recent advances in computer vision are the result of a healthy competition among researchers on high quality, task-specific, benchmarks. After a decade of active research, zero-shot learning (ZSL) models accuracy on the Imagenet…

Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and compare them with instance-level semantic predictions to infer…