PartImageNet: A Large, High-Quality Dataset of Parts
Authors:
Preprint
Abstract
It is natural to represent objects in terms of their parts. This has the potential to improve the performance of algorithms for object recognition and segmentation but can also help for downstream tasks like activity recognition. Research on part-based models, however, is hindered by the lack of datasets with per-pixel part annotations. This is partly due to the difficulty and high cost of annotating object parts so it has rarely been done except for humans (where there exists a big literature on part-based models). To help address this problem, we propose PartImageNet, a large, high-quality dataset with part segmentation annotations. It consists of $158$ classes from ImageNet with approximately $24,000$ images. PartImageNet is unique because it offers part-level annotations on a general set of classes including non-rigid, articulated objects, while having an order of magnitude larger size compared to existing part datasets (excluding datasets of humans). It can be utilized for many vision tasks including Object Segmentation, Semantic Part Segmentation, Few-shot Learning and Part Discovery. We conduct comprehensive experiments which study these tasks and set up a set of baselines. The dataset and scripts are released at https://github.com/TACJu/PartImageNet.
Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- Look into Person: Joint Body Parsing & Pose Estimation Network and a New BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Beyond PASCAL: A benchmark for 3D object detection in the wild2014
- Microsoft COCO: Common Objects in Context2014
- One-shot learning of object categoriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987
- The Representation and Matching of Pictorial StructuresIEEE Transactions on Computers, 1973