Few-shot object detection: A comprehensive survey

M Köhler, M Eisenbach… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
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 …

Machine learning for autonomous vehicle's trajectory prediction: A comprehensive survey, challenges, and future research directions

V Bharilya, N Kumar - Vehicular Communications, 2024 - Elsevier
The significant contribution of human errors, accounting for approximately 94%(with a
margin of±2.2%), to road crashes leading to casualties, vehicle damages, and safety …

Meta faster r-cnn: Towards accurate few-shot object detection with attentive feature alignment

G Han, S Huang, J Ma, Y He, SF Chang - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to
adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object …

Supervised masked knowledge distillation for few-shot transformers

H Lin, G Han, J Ma, S Huang, X Lin… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Vision Transformers (ViTs) emerge to achieve impressive performance on many
data-abundant computer vision tasks by capturing long-range dependencies among local …

Digeo: Discriminative geometry-aware learning for generalized few-shot object detection

J Ma, Y Niu, J Xu, S Huang, G Han… - Proceedings of the …, 2023 - openaccess.thecvf.com
Generalized few-shot object detection aims to achieve precise detection on both base
classes with abundant annotations and novel classes with limited training data. Existing …

Multi-modal queried object detection in the wild

Y Xu, M Zhang, C Fu, P Chen… - Advances in Neural …, 2024 - proceedings.neurips.cc
We introduce MQ-Det, an efficient architecture and pre-training strategy design to utilize both
textual description with open-set generalization and visual exemplars with rich description …

Explore the power of synthetic data on few-shot object detection

S Lin, K Wang, X Zeng, R Zhao - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Few-shot object detection (FSOD) aims to expand an object detector for novel categories
given only a few instances for training. The few training samples restrict the performance of …

Swin transformer based vehicle detection in undisciplined traffic environment

P Deshmukh, GSR Satyanarayana, S Majhi… - Expert Systems with …, 2023 - Elsevier
Intelligent vehicle detection (IVD) plays a prominent role in evolving an intelligent traffic
management system (ITMS). It can help to decrease the average waiting time at the traffic …

Fs-detr: Few-shot detection transformer with prompting and without re-training

A Bulat, R Guerrero, B Martinez… - Proceedings of the …, 2023 - openaccess.thecvf.com
This paper is on Few-Shot Object Detection (FSOD), where given a few templates
(examples) depicting a novel class (not seen during training), the goal is to detect all of its …

Breaking immutable: Information-coupled prototype elaboration for few-shot object detection

X Lu, W Diao, Y Mao, J Li, P Wang, X Sun… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Few-shot object detection, expecting detectors to detect novel classes with a few instances,
has made conspicuous progress. However, the prototypes extracted by existing meta …