One Shot Learning via Compositions of Meaningful Patches
By Alex Wong, Alan L. Yuille. 2015
46 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
- Martial Hebert
- Abhinav Kumar Gupta
- Sergey Levine
- Yu-Xiong Wang
- Ross B. Girshick
- Trevor Darrell
- Bharath Hariharan
- Bernt Schiele
In Computer Vision and Pattern Recognition
- Abhinav Kumar Gupta
- Luc Van Gool
- Jitendra Malik
- Trevor Darrell
- Dacheng Tao
- Martial Hebert
- Bernt Schiele
- Xiaogang Wang
Citations in the corpus
- The More You Know: Using Knowledge Graphs for Image Classification (2016, background): “ttribute pairs directly. We further evaluate our model on one and few-shot learning. There have been a few works in this area recently such as [2] which inverts the process that creates the input and [37] which learns new categories by finding common patches between classes. Both evaluate on handwrit”
- Low-Shot Learning from Imaginary Data (2018, background): “Often, these generative models have to be hand-designed for the domain, such as strokes [17, 18] or parts [39] for handwritten characters.”
- Deep Meta-Learning: Learning to Learn in the Concept Space (2018, background): “(Wong & Yuille, 2015) extend this idea to natural images without relying on domain knowledge.”
- Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector (2019, background): “Earlier works attempted to learn a general prior [29, 30, 31, 32, 33], such as hand-designed strokes or parts which can be shared across categories.”
- A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs (2017, methodology): “RCN outperformed the CNNs and the CPM (Fig.”
- Low-shot visual object recognition (2016, background): “For restricted domains such as hand-written characters [24, 21], there exist powerful generative models that compose characters from a dictionary of parts [41] or strokes [22].”
- Low-Shot Visual Recognition by Shrinking and Hallucinating Features (2016, background): “there exist powerful generative models that compose characters from a dictionary of parts [45] or strokes [25].”