paper-with-me

Papers

MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence

2023-01-01 · CVPR 2023 1 · Yixuan Sun, Yiwen Huang, Haijing Guo, Yuzhou Zhao, Runmin Wu, Yizhou Yu, Weifeng Ge, Wenqiang Zhang

Semantic correspondence have built up a new way for object recognition. However current single-object matching schema can be hard for discovering commonalities for a category and far from the real-world recognition tasks. To fill this gap, we design the multi-instance semantic correspondence task which aims at constructing the correspondence between multiple objects in an image pair. To support this task, we build a multi-instance semantic correspondence (MISC) dataset from COCO Detection 2017 task called MISC210K. We construct our dataset as three steps: (1) category selection and data cleaning; (2) keypoint design based on 3D models and object description rules; (3) human-machine collaborative annotation. Following these steps, we select 34 classes of objects with 4,812 challenging images annotated via a well designed semi-automatic workflow, and finally acquire 218,179 image pairs with instance masks and instance-level keypoint pairs annotated. We design a dual-path collaborative learning pipeline to train instance-level co-segmentation task and fine-grained level correspondence task together. Benchmark evaluation and further ablation results with detailed analysis are provided with three future directions proposed. Our project is available on https://github.com/YXSUNMADMAX/MISC210K.

📄 PDF Abstract BibTeX

Code (1)

yxsunmadmax/misc210k 공식 구현

Tasks

ObjectObject RecognitionSemantic correspondence

Similar Papers 제목 키워드 기반

Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances

2024-06-24 · Emma Hart, Quentin Renau, Kevin Sim, Mohamad Alissa

Deep neural networks (DNN) are increasingly being used to perform algorithm-selection in combinatorial optimisation domains, particularly as they accommodate input representations which avoid designing and calculating fe…

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

2023-06-02 · Eduardo Dadalto, Marco Romanelli, Georg Pichler, Pablo Piantanida

Misclassification detection is an important problem in machine learning, as it allows for the identification of instances where the model's predictions are unreliable. However, conventional uncertainty measures such as S…

image-classificationImage Classification

Cost-Sensitive Stacking: an Empirical Evaluation

2023-01-04 · Natalie Lawrance, Marie-Anne Guerry, George Petrides

Many real-world classification problems are cost-sensitive in nature, such that the misclassification costs vary between data instances. Cost-sensitive learning adapts classification algorithms to account for differences…

Classification

Data-Mining Textual Responses to Uncover Misconception Patterns

2017-03-24 · Joshua J. Michalenko, Andrew S. Lan, Richard G. Baraniuk

An important, yet largely unstudied, problem in student data analysis is to detect misconceptions from students' responses to open-response questions. Misconception detection enables instructors to deliver more targeted …

Misconceptions

Clarify: Improving Model Robustness With Natural Language Corrections

2024-02-06 · Yoonho Lee, Michelle S. Lam, Helena Vasconcelos, Michael S. Bernstein 외

The standard way to teach models is by feeding them lots of data. However, this approach often teaches models incorrect ideas because they pick up on misleading signals in the data. To prevent such misconceptions, we mus…

Misconceptionsmodel