Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method

by   Lu Zhang, et al.

Few-shot object detection (FSOD) is to detect objects with a few examples. However, existing FSOD methods do not consider hierarchical fine-grained category structures of objects that exist widely in real life. For example, animals are taxonomically classified into orders, families, genera and species etc. In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm. To this end, on the one hand, we build the first large-scale and high-quality Hi-FSOD benchmark dataset HiFSOD-Bird, which contains 176,350 wild-bird images falling to 1,432 categories. All the categories are organized into a 4-level taxonomy, consisting of 32 orders, 132 families, 572 genera and 1,432 species. On the other hand, we propose the first Hi-FSOD method HiCLPL, where a hierarchical contrastive learning approach is developed to constrain the feature space so that the feature distribution of objects is consistent with the hierarchical taxonomy and the model's generalization power is strengthened. Meanwhile, a probabilistic loss is designed to enable the child nodes to correct the classification errors of their parent nodes in the taxonomy. Extensive experiments on the benchmark dataset HiFSOD-Bird show that our method HiCLPL outperforms the existing FSOD methods.


page 1

page 2

page 3

page 4


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

Conventional methods for object detection usually requires substantial a...

FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery

With the rapid development of deep learning, many deep learning based ap...

Few-Shot Object Detection in Real Life: Case Study on Auto-Harvest

Confinement during COVID-19 has caused serious effects on agriculture al...

QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time

There are many real-life use cases such as barcode scanning or billboard...

Re-thinking Co-Salient Object Detection

In this paper, we conduct a comprehensive study on the co-salient object...

Universal-Prototype Augmentation for Few-Shot Object Detection

Few-shot object detection (FSOD) aims to strengthen the performance of n...

Application-Driven AI Paradigm for Hand-Held Action Detection

In practical applications especially with safety requirement, some hand-...

Please sign up or login with your details

Forgot password? Click here to reset