SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

08/27/2020
by   Alexander Wang, et al.
0

Sketch drawings are an intuitive visual domain that appeals to human instinct. Previous work has shown that recurrent neural networks are capable of producing sketch drawings of a single or few classes at a time. In this work we investigate representations developed by training a generative model to produce sketches from pixel images across many classes in a sketch domain. We find that the embeddings learned by this sketching model are informative for visual tasks and capture some forms of visual understanding. We then use them to exceed state-of-the-art performance in unsupervised few-shot classification on the Omniglot and mini-ImageNet benchmarks. We also leverage the generative capacity of our model to produce high quality sketches of novel classes based on just a single example.

READ FULL TEXT
research
04/11/2017

A Neural Representation of Sketch Drawings

We present sketch-rnn, a recurrent neural network (RNN) able to construc...
research
04/18/2019

Generative Model for Zero-Shot Sketch-Based Image Retrieval

We present a probabilistic model for Sketch-Based Image Retrieval (SBIR)...
research
03/29/2023

Sketch-an-Anchor: Sub-epoch Fast Model Adaptation for Zero-shot Sketch-based Image Retrieval

Sketch-an-Anchor is a novel method to train state-of-the-art Zero-shot S...
research
05/19/2020

Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt

Previous researches of sketches often considered sketches in pixel forma...
research
07/04/2020

BézierSketch: A generative model for scalable vector sketches

The study of neural generative models of human sketches is a fascinating...
research
05/29/2019

Learning Robust Global Representations by Penalizing Local Predictive Power

Despite their renowned predictive power on i.i.d. data, convolutional ne...
research
09/24/2021

Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild

This work investigates the problem of sketch-guided object localization ...

Please sign up or login with your details

Forgot password? Click here to reset