Add to ORKGSelf-supervision can dramatically cut back the amount of manually-labeled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabeled dataset of images using synthetic image transformations. It does so by means of a robust probabilistic formulation that can introspectively determine which image regions are likely to result in stable image matching. We show empirically that a network pre-trained in this ma...
The humanly constructed world is well-organized in space. A prominent feature of this artificial wor...
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark det...
Thesis (Ph.D.)--University of Washington, 2020Supervised training with deep Convolutional Neural Net...
Self-supervision can dramatically cut back the amount of manually-labelled data required to train de...
Self-supervision can dramatically cut back the amount of manually-labeled data required to train dee...
This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Con...
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nos...
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nos...
Learning automatically the structure of object categories remains an important open problem in compu...
This thesis aims at learning and predicting the fine-grained structure of visual object categories g...
Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable res...
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching me...
This thesis aims at learning and predicting the fine-grained structure of visual object categories g...
In this thesis, three well known self-supervised methods have been implemented and trained on road s...
In this thesis, three well known self-supervised methods have been implemented and trained on road s...
The humanly constructed world is well-organized in space. A prominent feature of this artificial wor...
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark det...
Thesis (Ph.D.)--University of Washington, 2020Supervised training with deep Convolutional Neural Net...
Self-supervision can dramatically cut back the amount of manually-labelled data required to train de...
Self-supervision can dramatically cut back the amount of manually-labeled data required to train dee...
This paper proposes a novel paradigm for the unsupervised learning of object landmark detectors. Con...
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nos...
We propose a method for learning landmark detectors for visual objects (such as the eyes and the nos...
Learning automatically the structure of object categories remains an important open problem in compu...
This thesis aims at learning and predicting the fine-grained structure of visual object categories g...
Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable res...
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching me...
This thesis aims at learning and predicting the fine-grained structure of visual object categories g...
In this thesis, three well known self-supervised methods have been implemented and trained on road s...
In this thesis, three well known self-supervised methods have been implemented and trained on road s...
The humanly constructed world is well-organized in space. A prominent feature of this artificial wor...
Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark det...
Thesis (Ph.D.)--University of Washington, 2020Supervised training with deep Convolutional Neural Net...