paper-with-me

홈 › Papers

Towards Open World Recognition

2014-12-18 · CVPR 2015 6 · Abhijit Bendale, Terrance Boult

With the of advent rich classification models and high computational power visual recognition systems have found many operational applications. Recognition in the real world poses multiple challenges that are not apparent in controlled lab environments. The datasets are dynamic and novel categories must be continuously detected and then added. At prediction time, a trained system has to deal with myriad unseen categories. Operational systems require minimum down time, even to learn. To handle these operational issues, we present the problem of Open World recognition and formally define it. We prove that thresholding sums of monotonically decreasing functions of distances in linearly transformed feature space can balance "open space risk" and empirical risk. Our theory extends existing algorithms for open world recognition. We present a protocol for evaluation of open world recognition systems. We present the Nearest Non-Outlier (NNO) algorithm which evolves model efficiently, adding object categories incrementally while detecting outliers and managing open space risk. We perform experiments on the ImageNet dataset with 1.2M+ images to validate the effectiveness of our method on large scale visual recognition tasks. NNO consistently yields superior results on open world recognition.

📄 PDF Abstract BibTeX arXiv:1412.5687

Code (0)

등록된 구현이 없습니다.

Tasks

Object Recognition

Similar Papers 제목 키워드 기반

Bayesian Embeddings for Few-Shot Open World Recognition

2021-07-29 · John Willes, James Harrison, Ali Harakeh, Chelsea Finn 외

As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents contin…

Decision MakingFew-Shot Learning

Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition

2024-02-29 · BoYu Chen, Siran Chen, Kunchang Li, Qinglin Xu 외

Open-world video recognition is challenging since traditional networks are not generalized well on complex environment variations. Alternatively, foundation models with rich knowledge have recently shown their generaliza…

Transfer LearningVideo Recognition

Learning for Transductive Threshold Calibration in Open-World Recognition

2023-05-19 · CVPR 2024 1 · Qin Zhang, Dongsheng An, Tianjun Xiao, Tong He 외

In deep metric learning for visual recognition, the calibration of distance thresholds is crucial for achieving desired model performance in the true positive rates (TPR) or true negative rates (TNR). However, calibratin…

Graph Neural NetworkMetric LearningOpen Set Learning

Towards Open-World Gesture Recognition

2024-01-20 · Junxiao Shen, Matthias De Lange, Xuhai "Orson" Xu, Enmin Zhou 외

Providing users with accurate gestural interfaces, such as gesture recognition based on wrist-worn devices, is a key challenge in mixed reality. However, static machine learning processes in gesture recognition assume th…

Continual LearningGesture RecognitionMixed Reality

Exploring the Open World Using Incremental Extreme Value Machines

2022-05-30 · Tobias Koch, Felix Liebezeit, Christian Riess, Vincent Christlein 외

Dynamic environments require adaptive applications. One particular machine learning problem in dynamic environments is open world recognition. It characterizes a continuously changing domain where only some classes are s…

Class Incremental LearningComputational EfficiencyFace Recognitionimage-classification+3