A Comparative Review of Recent Few-Shot Object Detection Algorithms

Abstract

Few-shot object detection, learning to adapt to the novel classes with a few labeled data, is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data and the urgent demands to cut costs of data collection and annotation. Recently, some studies have explored how to use implicit cues in extra datasets without target-domain supervision to help few-shot detectors refine robust task notions. This survey provides a comprehensive overview from current classic and latest achievements for few-shot object detection to future research expectations from manifold perspectives. In particular, we first propose a data-based taxonomy of the training data and the form of corresponding supervision which are accessed during the training stage. Following this taxonomy, we present a significant review of the formal definition, main challenges, benchmark datasets, evaluation metrics, and learning strategies. In addition, we present a detailed investigation of how to interplay the object detection methods to develop this issue systematically. Finally, we conclude with the current status of few-shot object detection, along with potential research directions for this field.

References in corpus (36)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• YOLOv3: An Incremental Improvement
• Prototypical Networks for Few-shot Learning
• Recurrent Neural Network Regularization
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Temporal Ensembling for Semi-Supervised Learning
• Object Detection in 20 Years: A Survey
• Semi-Supervised Learning with Generative Adversarial Networks
• On First-Order Meta-Learning Algorithms
• A Simple Semi-Supervised Learning Framework for Object Detection
• A Review of Object Detection Models based on Convolutional Neural Network
• An Overview of Deep Semi-Supervised Learning
• Good Semi-supervised Learning that Requires a Bad GAN
• Stacked What-Where Auto-encoders
• TADAM: Task dependent adaptive metric for improved few-shot learning
• Few-Example Object Detection with Model Communication
• Investigating Human Priors for Playing Video Games
• LSTD: A Low-Shot Transfer Detector for Object Detection
• Augmentation for small object detection
• Meta-learning for Few-shot Natural Language Processing: A Survey
• Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses
• Restoring Negative Information in Few-Shot Object Detection
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• One-Shot Object Detection without Fine-Tuning
• Cooperating RPN's Improve Few-Shot Object Detection
• Class-Incremental Few-Shot Object Detection
• Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization
• Dual-Awareness Attention for Few-Shot Object Detection
• Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
• MM-FSOD: Meta and metric integrated few-shot object detection
• Review. Machine learning techniques for traffic sign detection
• A Concise Review of Recent Few-shot Meta-learning Methods
• AFD-Net: Adaptive Fully-Dual Network for Few-Shot Object Detection