Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark

06/28/2022
by   Chang Xu, et al.
0

Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels. State-of-the-art object detectors do not provide satisfactory results on tiny objects due to the lack of supervision from discriminative features. Our key observation is that the Intersection over Union (IoU) metric and its extensions are very sensitive to the location deviation of the tiny objects, which drastically deteriorates the quality of label assignment when used in anchor-based detectors. To tackle this problem, we propose a new evaluation metric dubbed Normalized Wasserstein Distance (NWD) and a new RanKing-based Assigning (RKA) strategy for tiny object detection. The proposed NWD-RKA strategy can be easily embedded into all kinds of anchor-based detectors to replace the standard IoU threshold-based one, significantly improving label assignment and providing sufficient supervision information for network training. Tested on four datasets, NWD-RKA can consistently improve tiny object detection performance by a large margin. Besides, observing prominent noisy labels in the Tiny Object Detection in Aerial Images (AI-TOD) dataset, we are motivated to meticulously relabel it and release AI-TOD-v2 and its corresponding benchmark. In AI-TOD-v2, the missing annotation and location error problems are considerably mitigated, facilitating more reliable training and validation processes. Embedding NWD-RKA into DetectoRS, the detection performance achieves 4.3 AP points improvement over state-of-the-art competitors on AI-TOD-v2. Datasets, codes, and more visualizations are available at: https://chasel-tsui.github.io/AI-TOD-v2/

READ FULL TEXT

page 2

page 4

page 5

page 9

page 15

research
10/26/2021

A Normalized Gaussian Wasserstein Distance for Tiny Object Detection

Detecting tiny objects is a very challenging problem since a tiny object...
research
08/18/2022

RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection

Detecting tiny objects is one of the main obstacles hindering the develo...
research
08/03/2020

Reducing Label Noise in Anchor-Free Object Detection

Current anchor-free object detectors label all the features that spatial...
research
05/28/2022

Point RCNN: An Angle-Free Framework for Rotated Object Detection

Rotated object detection in aerial images is still challenging due to ar...
research
04/18/2023

Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection

Detecting arbitrarily oriented tiny objects poses intense challenges to ...
research
12/13/2021

Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images

Object detection has made tremendous strides in computer vision. Small o...
research
06/18/2021

Bridging the Gap Between Object Detection and User Intent via Query-Modulation

When interacting with objects through cameras, or pictures, users often ...

Please sign up or login with your details

Forgot password? Click here to reset