Latentkeypointgan: Controlling gans via latent keypoints
Generative adversarial networks (GANs) have attained photo-realistic quality in image
generation. However, how to best control the image content remains an open challenge. We …
generation. However, how to best control the image content remains an open challenge. We …
Task-independent knowledge makes for transferable representations for generalized zero-shot learning
Abstract Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by
learning transferable image representations. Existing methods find that, by aligning image …
learning transferable image representations. Existing methods find that, by aligning image …
From keypoints to object landmarks via self-training correspondence: A novel approach to unsupervised landmark discovery
This paper proposes a novel paradigm for the unsupervised learning of object landmark
detectors. Contrary to existing methods that build on auxiliary tasks such as image …
detectors. Contrary to existing methods that build on auxiliary tasks such as image …
Lead: Self-supervised landmark estimation by aligning distributions of feature similarity
In this work, we introduce LEAD, an approach to discover landmarks from an unannotated
collection of category-specific images. Existing works in self-supervised landmark detection …
collection of category-specific images. Existing works in self-supervised landmark detection …
Unsupervised landmark discovery via self-training correspondence
D Mallis - 2023 - eprints.nottingham.ac.uk
Object parts, also known as landmarks, convey information about an object's shape and
spatial configuration in 3D space, especially for deformable objects. The goal of landmark …
spatial configuration in 3D space, especially for deformable objects. The goal of landmark …