paper-with-me

홈 › Papers

SketchEmbedNet: Learning Novel Concepts by Imitating Drawings

2020-08-27 · Alexander Wang, Mengye Ren, Richard S. Zemel

Sketch drawings capture the salient information of visual concepts. Previous work has shown that neural networks are capable of producing sketches of natural objects drawn from a small number of classes. While earlier approaches focus on generation quality or retrieval, we explore properties of image representations learned by training a model to produce sketches of images. We show that this generative, class-agnostic model produces informative embeddings of images from novel examples, classes, and even novel datasets in a few-shot setting. Additionally, we find that these learned representations exhibit interesting structure and compositionality.

📄 PDF Abstract BibTeX arXiv:2009.04806

Code (1)

alexnwang/SketchEmbedNet-public tf

Tasks

Novel ConceptsRetrieval

Similar Papers 제목 키워드 기반

Visual communication of object concepts at different levels of abstraction

2021-06-05 · Justin Yang, Judith E. Fan

People can produce drawings of specific entities (e.g., Garfield), as well as general categories (e.g., "cat"). What explains this ability to produce such varied drawings of even highly familiar object concepts? We hypot…

Constructing a Norm for Children's Scientific Drawing: Distribution Features Based on Semantic Similarity of Large Language Models

2025-02-21 · Yi Zhang, Fan Wei, Jingyi Li, Yan Wang 외

The use of children's drawings to examining their conceptual understanding has been proven to be an effective method, but there are two major problems with previous research: 1. The content of the drawings heavily relies…

Large Language ModelSemantic SimilaritySemantic Textual Similarity

Photo-Sketching: Inferring Contour Drawings from Images

2019-01-02 · Mengtian Li, Zhe Lin, Radomir Mech, Ersin Yumer 외

Edges, boundaries and contours are important subjects of study in both computer graphics and computer vision. On one hand, they are the 2D elements that convey 3D shapes, on the other hand, they are indicative of occlusi…

Boundary DetectionDiversity

See and Copy: Generation of complex compositional movements from modular and geometric RNN representations

2022-10-05 · Sunny Duan, Mikail Khona, Adrian Bertagnoli, Sarthak Chandra 외

A hallmark of biological intelligence and control is combinatorial generalization: animals are able to learn various things, then piece them together in new combinations to produce appropriate outputs for new tasks. Insp…

Learning to Sketch with Deep Q Networks and Demonstrated Strokes

2018-10-14 · Tao Zhou, Chen Fang, Zhaowen Wang, Jimei Yang 외

Doodling is a useful and common intelligent skill that people can learn and master. In this work, we propose a two-stage learning framework to teach a machine to doodle in a simulated painting environment via Stroke Demo…

Q-Learning