Few-Shot Open-Set Recognition Using Meta-Learning

Liu, Bo; Kang, Hao; Li, Haoxiang; Hua, Gang; Vasconcelos, Nuno

doi:10.1109/cvpr42600.2020.00882

Cited by 78 publications

(94 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Related Workmentioning

confidence: 99%

“…There exist many research works on this topic, mostly concentrating on few-shot classification [35,58,6,31,43,53,9,3,21,46,37,17,22,11,32,36,42,63,26,25]. Most of these works [9,3,21,46,37,17,22,11,32,36,42,26] adopt meta-learning techniques to attack few-shot classification task. Besides, some other approaches [49,45,47,44,2] are based on distance metric learning (DML), which try to learn feature representations that preserve the category neighborhood structure under certain distance metric, where features corresponding to the same category are closer than features from different categories.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

PNPDet: Efficient Few-shot Detection without Forgetting via Plug-and-Play Sub-networks

Zhang

Cui

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

The human visual system can detect objects of unseen categories from merely a few examples. However, such capability remains absent in state-of-the-art detectors. To bridge this gap, several attempts have been proposed to perform few-shot detection by incorporating meta-learning techniques. Such methods can improve detection performance on unseen categories, but also add huge computational burden, and usually degrade detection performance on seen categories. In this paper, we present PNPDet, a novel Plug-and-Play Detector, for efficient few-shot detection without forgetting. It introduces a simple but effective architecture with separate sub-networks that disentangles the recognition of base and novel categories and prevents hurting performance on known categories while learning new concepts. Distance metric learning is further incorporated into sub-networks, consistently boosting detection performance for both base and novel categories. Experiments show that the proposed PNPDet can achieve comparable few-shot detection performance on unseen categories while not losing accuracy on seen categories, and also remain efficient and flexible at the same time.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

PNPDet: Efficient Few-shot Detection without Forgetting via Plug-and-Play Sub-networks

Zhang

Cui

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…As an attempt to overcome these difficulties, Fort [22] tried confidence region estimation in the embedding space in the form of a Gaussian covariance matrix and used it to construct metrics. Liu et al [24] proposed to use of a new metric learning formula based on Mahalanobis distance [25] to avoid the tendency to overfit the training class. However, these methods still have difficulty in estimating the covariance matrix of each class under the few-shot setting.…”

Section: Few-shot Classification Problemmentioning

confidence: 99%

“…This approach seems to be appropriate for the situation that the number of labeled samples for test classes is very limited because classifiers with high complexity can be easily overfitted to the few given samples. Although computational experiments have shown that a simple classifier combined with a well-generalized embedding module can achieve 2 of 15 good performance [21], there would be further room for improvement in the classification module [22][23][24]. In this paper, we try to improve the performance of the few-shot classifiers by elaborating on the distance-based classification module.…”

Section: Introductionmentioning

confidence: 99%

Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification

Lee

Park

2021

Applied Sciences

View full text Add to dashboard Cite

In developing a few-shot classification model using deep networks, the limited number of samples in each class causes difficulty in utilizing statistical characteristics of the class distributions. In this paper, we propose a method to treat this difficulty by combining a probabilistic similarity based on intra-class statistics with a metric-based few-shot classification model. Noting that the probabilistic similarity estimated from intra-class statistics and the classifier of conventional few-shot classification models have a common assumption on the class distributions, we propose to apply the probabilistic similarity to obtain loss value for episodic learning of embedding network as well as to classify unseen test data. By defining the probabilistic similarity as the probability density of difference vectors between two samples with the same class label, it is possible to obtain a more reliable estimate of the similarity especially for the case of large number of classes. Through experiments on various benchmark data, we confirm that the probabilistic similarity can improve the classification performance, especially when the number of classes is large.

show abstract

“…In this thesis, we also apply OSR methods to fault detection on time-series data in the industrial field. In these years, many researchers study on developing OSR technique in other tasks, such as semantic segmentation [94], few shot learning [95], long-tailed recognition [96], and 3-dimensional cloud point classification [97]. We will explore to develop and apply OSR methods to other tasks in the future.…”

Section: Future Workmentioning

confidence: 99%

A study on open set recognition methods

Sun¹

View full text Add to dashboard Cite

Ling Keck-Voon. He constantly encouraged and supported me throughout my Ph.D. career. He has helped me a lot in how to do academic research, in-depth thinking, and manuscript writing. I would like to thank Professor Lin Guoshen for his patient guidance and for leading me into the wonderful world of deep learning. Also, I would like to thank Nanyang Technological University, National Research Foundation Singapore, and SMRT Corporation for funding my education and research.

show abstract

Few-Shot Open-Set Recognition Using Meta-Learning

Cited by 78 publications

References 14 publications

PNPDet: Efficient Few-shot Detection without Forgetting via Plug-and-Play Sub-networks

PNPDet: Efficient Few-shot Detection without Forgetting via Plug-and-Play Sub-networks

Effect of Probabilistic Similarity Measure on Metric-Based Few-Shot Classification

A study on open set recognition methods

Contact Info

Product

Resources

About