Incremental Few-Shot Object Detection

Pérez-Rúa, Juan-Manuel; Zhu, Xiatian; Hospedales, Timothy M.; Xiang, Tao

doi:10.1109/cvpr42600.2020.01386

Cited by 220 publications

(137 citation statements)

References 35 publications

(2 reference statements)

Supporting

Mentioning

123

Contrasting

Order By: Relevance

“…Perez-Rua et al [ 116 ] proposed OpeN-ended Centre nET (ONCE) for solving the problem of incremental object detection and segmentation. ONCE is based on the structure of CentreNet [ 117 ] and splits it into a feature extractor and an object locator.…”

Section: Methods Descriptionmentioning

confidence: 99%

An Appraisal of Incremental Learning Methods

Luo

Yin

Bai

et al. 2020

Entropy

View full text Add to dashboard Cite

As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However, incremental learning remains a long term challenge. Modern deep neural network models achieve outstanding performance on stationary data distributions with batch training. This restriction leads to catastrophic forgetting for incremental learning scenarios since the distribution of incoming data is unknown and has a highly different probability from the old data. Therefore, a model must be both plastic to acquire new knowledge and stable to consolidate existing knowledge. This review aims to draw a systematic review of the state of the art of incremental learning methods. Published reports are selected from Web of Science, IEEEXplore, and DBLP databases up to May 2020. Each paper is reviewed according to the types: architectural strategy, regularization strategy and rehearsal and pseudo-rehearsal strategy. We compare and discuss different methods. Moreover, the development trend and research focus are given. It is concluded that incremental learning is still a hot research area and will be for a long period. More attention should be paid to the exploration of both biological systems and computational models.

show abstract

Section: Methods Descriptionmentioning

confidence: 99%

An Appraisal of Incremental Learning Methods

Luo

Yin

Bai

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…[172] [169] [173] Feed-Forward model SNAIL [38], CNAP [107]. [44], [83], [174], [175] [176]- [178] PEARL [110]. [23], [112] Metric MatchingNets [87], ProtoNets [22], RelationNets [88].…”

Section: Gradient Rl Evolutionmentioning

confidence: 99%

“…However, performance is still far behind that of fully supervised methods, so there is more work to be done. Current research issues include improving cross-domain generalization [115], recognition within the joint label space defined by metatrain and meta-test classes [81], and incremental addition of new few-shot classes [133], [174].…”

Section: Classificationmentioning

confidence: 99%

“…Object Detection Building on progress in few-shot classification, few-shot object detection [174], [204] has been demonstrated, often using feed-forward hypernetworkbased approaches to embed support set images and synthesize final layer classification weights in the base model. Landmark Prediction aims to locate a skeleton of key points within an image, such as such as joints of a human or robot.…”

Section: Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Meta-Learning in Neural Networks: A Survey

Hospedales¹,

Antoniou²,

Micaelli³

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

779

371

View full text Add to dashboard Cite

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple learning episodes. This paradigm provides an opportunity to tackle many conventional challenges of deep learning, including data and computation bottlenecks, as well as generalization. This survey describes the contemporary meta-learning landscape. We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today. We survey promising applications and successes of meta-learning such as few-shot learning and reinforcement learning. Finally, we discuss outstanding challenges and promising areas for future research.

show abstract

“…MAML [ 36 ] seeks to learn a model initialization trained on multiple tasks and could be adapted to the target task with a few annotated data points. It has been widely used in the field of computer vision, involving visual tracking [ 37 ], incremental object detection [ 38 ], and semantic segmentation [ 39 ]. MAML has also been applied to many NLP tasks such as text classification [ 40 ], named entity recognition [ 41 ], and relation extraction [ 42 ].…”

Section: Related Workmentioning

confidence: 99%

Enhancement of Target‐Oriented Opinion Words Extraction with Multiview‐Trained Machine Reading Comprehension Model

Zhang

Guo

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Target-oriented opinion words extraction (TOWE) seeks to identify opinion expressions oriented to a specific target, and it is a crucial step toward fine-grained opinion mining. Recent neural networks have achieved significant success in this task by building target-aware representations. However, there are still two limitations of these methods that hinder the progress of TOWE. Mainstream approaches typically utilize position indicators to mark the given target, which is a naive strategy and lacks task-specific semantic meaning. Meanwhile, the annotated target-opinion pairs contain rich latent structural knowledge from multiple perspectives, but existing methods only exploit the TOWE view. To tackle these issues, we formulate the TOWE task as a question answering (QA) problem and leverage a machine reading comprehension (MRC) model trained with a multiview paradigm to extract targeted opinions. Specifically, we introduce a template-based pseudo-question generation method and utilize deep attention interaction to build target-aware context representations and extract related opinion words. To take advantage of latent structural correlations, we further cast the opinion-target structure into three distinct yet correlated views and leverage meta-learning to aggregate common knowledge among them to enhance the TOWE task. We evaluate the proposed model on four benchmark datasets, and our method achieves new state-of-the-art results. Extensional experiments have shown that the pipeline method with our approach could surpass existing opinion pair extraction models, including joint methods that are usually believed to work better.

show abstract

Incremental Few-Shot Object Detection

Cited by 220 publications

References 35 publications

An Appraisal of Incremental Learning Methods

An Appraisal of Incremental Learning Methods

Meta-Learning in Neural Networks: A Survey

Enhancement of Target‐Oriented Opinion Words Extraction with Multiview‐Trained Machine Reading Comprehension Model

Contact Info

Product

Resources

About