A Survey of Deep Learning for Low-Shot Object Detection
- URL: http://arxiv.org/abs/2112.02814v4
- Date: Wed, 25 Oct 2023 12:44:30 GMT
- Title: A Survey of Deep Learning for Low-Shot Object Detection
- Authors: Qihan Huang, Haofei Zhang, Mengqi Xue, Jie Song, Mingli Song
- Abstract summary: Low-Shot Object Detection (LSOD) is an emerging research topic of detecting objects from a few or even no annotated samples.
This survey provides a comprehensive review of LSOD methods.
- Score: 44.20187548691372
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Object detection has achieved a huge breakthrough with deep neural networks
and massive annotated data. However, current detection methods cannot be
directly transferred to the scenario where the annotated data is scarce due to
the severe overfitting problem. Although few-shot learning and zero-shot
learning have been extensively explored in the field of image classification,
it is indispensable to design new methods for object detection in the
data-scarce scenario since object detection has an additional challenging
localization task. Low-Shot Object Detection (LSOD) is an emerging research
topic of detecting objects from a few or even no annotated samples, consisting
of One-Shot Object Detection (OSOD), Few-Shot Object Detection (FSOD) and
Zero-Shot Object Detection (ZSD). This survey provides a comprehensive review
of LSOD methods. First, we propose a thorough taxonomy of LSOD methods and
analyze them systematically, comprising some extensional topics of LSOD
(semi-supervised LSOD, weakly-supervised LSOD, and incremental LSOD). Then, we
indicate the pros and cons of current LSOD methods with a comparison of their
performance. Finally, we discuss the challenges and promising directions of
LSOD to provide guidance for future works.
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) - Few-Shot Object Detection: Research Advances and Challenges [15.916463121997843]
Few-shot object detection (FSOD) combines few-shot learning and object detection techniques to rapidly adapt to novel objects with limited annotated samples.
This paper presents a comprehensive survey to review the significant advancements in the field of FSOD in recent years.
arXiv Detail & Related papers (2024-04-07T03:37:29Z) - Semi-supervised Open-World Object Detection [74.95267079505145]
We introduce a more realistic formulation, named semi-supervised open-world detection (SS-OWOD)
We demonstrate that the performance of the state-of-the-art OWOD detector dramatically deteriorates in the proposed SS-OWOD setting.
Our experiments on 4 datasets including MS COCO, PASCAL, Objects365 and DOTA demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2024-02-25T07:12:51Z) - Remote Sensing Object Detection Meets Deep Learning: A Meta-review of
Challenges and Advances [51.70835702029498]
This review aims to present a comprehensive review of the recent achievements in deep learning based RSOD methods.
We identify five main challenges in RSOD, including multi-scale object detection, rotated object detection, weak object detection, tiny object detection, and object detection with limited supervision.
We also review the widely used benchmark datasets and evaluation metrics within the field of RSOD, as well as the application scenarios for RSOD.
arXiv Detail & Related papers (2023-09-13T06:48:32Z) - Improved Region Proposal Network for Enhanced Few-Shot Object Detection [23.871860648919593]
Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches.
We develop a semi-supervised algorithm to detect and then utilize unlabeled novel objects as positive samples during the FSOD training stage.
Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception of the object detection model for large objects.
arXiv Detail & Related papers (2023-08-15T02:35:59Z) - 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) - Discovery-and-Selection: Towards Optimal Multiple Instance Learning for
Weakly Supervised Object Detection [86.86602297364826]
We propose a discoveryand-selection approach fused with multiple instance learning (DS-MIL)
Our proposed DS-MIL approach can consistently improve the baselines, reporting state-of-the-art performance.
arXiv Detail & Related papers (2021-10-18T07:06:57Z) - Deep Learning for Weakly-Supervised Object Detection and Object
Localization: A Survey [37.545083067084306]
Weakly-Supervised Object Detection (WSOD) and localization (WSOL) are long-standing and challenging CV tasks.
With the success of deep neural networks in object detection, both WSOD and WSOL have received unprecedented attention.
Hundreds of WSOD and WSOL methods and numerous techniques have been proposed in the deep learning era.
arXiv Detail & Related papers (2021-05-26T17:15:53Z) - Progressive Object Transfer Detection [84.48927705173494]
We propose a novel Progressive Object Transfer Detection (POTD) framework.
First, POTD can leverage various object supervision of different domains effectively into a progressive detection procedure.
Second, POTD consists of two delicate transfer stages, i.e., Low-Shot Transfer Detection (LSTD), and Weakly-Supervised Transfer Detection (WSTD)
arXiv Detail & Related papers (2020-02-12T00:16:24Z)
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.