Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector

By Qi Fan, Wei Zhuo, Yu-Wing Tai. Computer Vision and Pattern Recognition, 2019

642 citations recorded by the source corpus.

Conventional methods for object detection typically require a substantial amount of training data and preparing such high-quality training data is very labor-intensive. In this paper, we propose a novel few-shot object detection network that aims at detecting objects of unseen categories with only a few annotated examples. Central to our method are our Attention-RPN, Multi-Relation Detector and Contrastive Training strategy, which exploit the similarity between the few shot support set and query set to detect novel objects while suppressing false detection in the background. To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations. To the best of our knowledge, this is one of the first datasets specifically designed for few-shot object detection. Once our few-shot network is trained, it can detect objects of unseen categories without further training or fine-tuning. Our method is general and has a wide range of potential applications. We produce a new state-of-the-art performance on different datasets in the few-shot setting. The dataset link is https://github.com/fanq15/Few-Shot-Object-Detection-Dataset.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/58d20519b190308d144d4b0110527231179ea100

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey on Vision Transformer (2020, background): “GCNet [13] finds that the global contexts modeled by non-local operations are almost the same for different query positions within an image, and proposes to unify the simplified formulation and SENet [54] into a general framework for global context modeling [73, 52, 34, 93].”
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation (2021, background): “Few-shots learning can be considered as a matching problem where the query is compared with every element in the support set [43, 44, 45, 46].”
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection (2020, methodology): “Subsequent works [17,8,16,41] strengthen this pipeline by bringing more advanced methods on few-shot image classification, and commonly emphasize to improve classification performance of Region-of-Interest (RoI) in FSOD by using metric learning techniques.”
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (2021, background): “In few-shot detection, one might naturally conjecture the localization of novel objects is going to under-perform its base categories counterpart, with the concern that rare objects would be deemed as background [14, 13, 18].”
Reinforced Attention for Few-Shot Learning and Beyond (2021, background): “To fully make use of the available spatial information, attention-oriented designs are recently developed for few-shot learning [53, 55, 7, 62, 42, 16, 9].”
LARGE: Latent-Based Regression through GAN Semantics (2021, methodology): “In the context of visual media, such methods have been widely studied for classiﬁcation [55,59,64], object detection [13,67] and segmentation [12, 42].”
Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax (2020, background): “Compared with balanced distribution targeted object detection [12, 33, 1], and few-shot object detection [20, 3, 41, 11], the challenging and practical long-tail object detection problem is still underexplored.”
Research Progress on Few-Shot Learning for Remote Sensing Image Interpretation (2021, background): “…and has gained signiﬁcant improvement on the interpretation of natural images, including image classiﬁcation [17], [18], object detection [19], [20], semantic segmentation [21], [22], etc. Inspired by their successful applications in natural images, extensive efforts had been made by…”
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection (2021, methodology): “We take two popular evaluation protocols into consideration to access the effectiveness of our approach, including few-shot object detection (FSOD) and generalized few-shot object detection (G-FSOD).”