Locality and compositionality in zero-shot learning

By Tristan Sylvain, Linda Petrini, R. Devon Hjelm. 2019

56 citations recorded by the source corpus.

In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these properties in learned representations, we impose the additional constraint that, differently from most recent work in ZSL, no pre-training on different datasets (e.g. ImageNet) is performed. The results of our experiments show how locality, in terms of small parts of the input, and compositionality, i.e. how well can the learned representations be expressed as a function of a smaller vocabulary, are both deeply related to generalization and motivate the focus on more local-aware models in future research directions for representation learning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Representation & Self-Supervised Learning

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

In Radiology, Nuclear Medicine and Imaging

In Representation & Self-Supervised Learning

Citations in the corpus

Object-Centric Image Generation from Layouts (2020, background): “These points explain their use in higher-level visual reasoning tasks such as visual question answering [56] and zero-shot learning [54], and also motivate the use of scene graph-based retrieval in our model.”
Attribute Prototype Network for Zero-Shot Learning (2020, background): “[37] shows the importance of locality and compositionality of image representations for zero-shot learning.”
A Review of Generalized Zero-Shot Learning Methods (2020, background): “[111] empirically highlighted the importance of focusing on local image regions (via attention) as well as combining local knowledge to recognize the unseen classes.”
Open-vocabulary Attribute Detection (2022, background): “Another line of work [1,42,47] focuses on zero-shot object classification by inferring the attributes of an object as an intermediate step or relying on object-attribute compositionality [1, 8, 28] for zero-shot attribute-object classification.”
Contrastive Learning with Hard Negative Samples (2020, background): “Most contrastive methods are unsupervised, however there exist some that use label information (Sylvain et al., 2020; Khosla et al., 2020).”
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, background): “A similar study found that the same definition of compositionality is related to zero-shot generalization on vision tasks (Sylvain et al., 2020).”