Few-Shot Object Detection: A Survey
- URL: http://arxiv.org/abs/2112.11699v1
- Date: Wed, 22 Dec 2021 07:08:53 GMT
- Title: Few-Shot Object Detection: A Survey
- Authors: Mona K\"ohler, Markus Eisenbach and Horst-Michael Gross
- Abstract summary: Few-shot object detection aims to learn from few object instances of new categories in the target domain.
We categorize approaches according to their training scheme and architectural layout.
We introduce commonly used datasets and their evaluation protocols and analyze reported benchmark results.
- Score: 4.266990593059534
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Humans are able to learn to recognize new objects even from a few examples.
In contrast, training deep-learning-based object detectors requires huge
amounts of annotated data. To avoid the need to acquire and annotate these huge
amounts of data, few-shot object detection aims to learn from few object
instances of new categories in the target domain. In this survey, we provide an
overview of the state of the art in few-shot object detection. We categorize
approaches according to their training scheme and architectural layout. For
each type of approaches, we describe the general realization as well as
concepts to improve the performance on novel categories. Whenever appropriate,
we give short takeaways regarding these concepts in order to highlight the best
ideas. Eventually, we introduce commonly used datasets and their evaluation
protocols and analyze reported benchmark results. As a result, we emphasize
common challenges in evaluation and identify the most promising current trends
in this emerging field of few-shot object detection.
Related papers
- Beyond Few-shot Object Detection: A Detailed Survey [25.465534270637523]
Researchers have introduced few-shot object detection (FSOD) approaches that merge few-shot learning and object detection principles.
These approaches play a vital role in reducing the reliance on extensive labeled datasets.
This survey paper aims to provide a comprehensive understanding of the above-mentioned few-shot settings and explore the methodologies for each FSOD task.
arXiv Detail & Related papers (2024-08-26T13:09:23Z) - Deep Learning-Based Object Pose Estimation: A Comprehensive Survey [73.74933379151419]
We discuss the recent advances in deep learning-based object pose estimation.
Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks.
arXiv Detail & Related papers (2024-05-13T14:44:22Z) - Exploiting Unlabeled Data with Vision and Language Models for Object
Detection [64.94365501586118]
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets.
We propose a novel method that leverages the rich semantics available in recent vision and language models to localize and classify objects in unlabeled images.
We demonstrate the value of the generated pseudo labels in two specific tasks, open-vocabulary detection and semi-supervised object detection.
arXiv Detail & Related papers (2022-07-18T21:47:15Z) - Incremental-DETR: Incremental Few-Shot Object Detection via
Self-Supervised Learning [60.64535309016623]
We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector.
To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision.
We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
arXiv Detail & Related papers (2022-05-09T05:08:08Z) - Contrastive Object Detection Using Knowledge Graph Embeddings [72.17159795485915]
We compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs.
We propose a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.
arXiv Detail & Related papers (2021-12-21T17:10:21Z) - A Comparative Review of Recent Few-Shot Object Detection Algorithms [0.0]
Few-shot object detection, learning to adapt to the novel classes with a few labeled data, is an imperative and long-lasting problem.
Recent studies have explored how to use implicit cues in extra datasets without target-domain supervision to help few-shot detectors refine robust task notions.
arXiv Detail & Related papers (2021-10-30T07:57:11Z) - A Survey of Self-Supervised and Few-Shot Object Detection [19.647681501581225]
Self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection.
Few-shot object detection is about training a model on novel (unseen) object classes with little data.
In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection.
arXiv Detail & Related papers (2021-10-27T18:55:47Z) - Learning Open-World Object Proposals without Learning to Classify [110.30191531975804]
We propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlaps with any ground-truth object.
This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization.
arXiv Detail & Related papers (2021-08-15T14:36:02Z) - Closing the Generalization Gap in One-Shot Object Detection [92.82028853413516]
We show that the key to strong few-shot detection models may not lie in sophisticated metric learning approaches, but instead in scaling the number of categories.
Future data annotation efforts should therefore focus on wider datasets and annotate a larger number of categories.
arXiv Detail & Related papers (2020-11-09T09:31:17Z) - Few-Shot Object Detection via Knowledge Transfer [21.3564383157159]
Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes.
In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples.
arXiv Detail & Related papers (2020-08-28T06:35:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.