Learning to detect unseen object classes by between-class attribute transfer

By Christoph H. Lampert, Hannes Nickisch, Stefan Harmeling. 2009

2,672 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Microsoft COCO: Common Objects in Context (2014, background): “Datasets have also been created to recognize both scene [9] and object attributes [8], [38].”
Learning Transferable Visual Models From Natural Language Supervision (2021, background): “In computer vision, zero-shot learning usually refers to the study of generalizing to unseen object categories in image classification (Lampert et al., 2009).”
Zero-Shot Learning Through Cross-Modal Transfer (2013, background): “[21] construct a set of binary attributes for the image classes that convey various visual characteristics, such as “furry” and “paws” for bears and “wings” and “flies” for birds.”
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP (2021, background): “Zero-shot transfer learning (Lampert et al., 2009) is one of the most ambitious goals in vision, since it would improve various real-world downstream applications.”
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, background): “The research topic has witnessed two types of distinctive notions of zero-shot: the traditional class-level zero-shot that usually refers to the study of generalizing to unseen object categories [30], and the recently popular task-level zero-shot that refers to the study of generalizing to unseen da”
Continual Lifelong Learning with Neural Networks: A Review (2018, background): “limited amount of) particular samples, assuming the simultaneous availability of multiple 17 learning tasks with the aim to improve the performance at one speciﬁc task. Similarly, zero-shot learning (Lampert et al., 2009; Palatucci et al., 2009) and one-shot learning (Fei-Fei et al., 2003; Vinyals e”
A theory of independent mechanisms for extrapolation in generative models (2020, background): “Broadly construed, this also relates to zero-shot learning (Lampert, Nickisch, and Harmeling 2009) and notions of extrapolations explored in the context of dynamical systems (Martius and Lampert 2016).”
Concept Bottleneck Models (2020, background): “Models that bottleneck on human-specified concepts—where the model first predicts the concepts, then uses only those predicted concepts to make a final prediction—have been previously used for specific applications (Kumar et al., 2009; Lampert et al., 2009).”
Transductive Multi-View Zero-Shot Learning (2015, methodology): “Common semantic representations include binary vectors of visual attributes [27], [31], [15] (e.g. ’hasTail’ in Fig.”
Lifelong Learning with Dynamically Expandable Networks (2017, neutral): “This dataset consists of 30, 475 images of 50 animals (Lampert et al., 2009).”
Gradient Episodic Memory for Continual Learning (2017, background): “Zero-shot learning [Lampert et al., 2009, Palatucci et al., 2009] and one-shot learning [Fei-Fei et al., 2003, Vinyals et al., 2016, Santoro et al., 2016, Bertinetto et al., 2016] aim at performing well on unseen tasks, but ignore the catastrophic forgetting of previously learned tasks.”
PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “Further works should investigate how to exploit the already present future information with Zeroshot [42, 41] as already done in semantic segmentation [36, 5] and explored for continual classification [72, 19].”
Efficient Lifelong Learning with A-GEM (2018, methodology): “In our experiments, we use the latter since it is provided with popular benchmark datasets (Wah et al., 2011; Lampert et al., 2009).”