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

12/13/2021
by   Dong Liang, et al.
28

Object detection has made tremendous strides in computer vision. Small object detection with appearance degradation is a prominent challenge, especially for aerial observations. To collect sufficient positive/negative samples for heuristic training, most object detectors preset region anchors in order to calculate Intersection-over-Union (IoU) against the ground-truthed data. In this case, small objects are frequently abandoned or mislabeled. In this paper, we present an effective Dynamic Enhancement Anchor (DEA) network to construct a novel training sample generator. Different from the other state-of-the-art techniques, the proposed network leverages a sample discriminator to realize interactive sample screening between an anchor-based unit and an anchor-free unit to generate eligible samples. Besides, multi-task joint training with a conservative anchor-based inference scheme enhances the performance of the proposed model while reducing computational complexity. The proposed scheme supports both oriented and horizontal object detection tasks. Extensive experiments on two challenging aerial benchmarks (i.e., DOTA and HRSC2016) indicate that our method achieves state-of-the-art performance in accuracy with moderate inference speed and computational overhead for training. On DOTA, our DEA-Net which integrated with the baseline of RoI-Transformer surpasses the advanced method by 0.40 detection with a weaker backbone network (ResNet-101 vs ResNet-152) and 3.08 mean-Average-Precision (mAP) for horizontal object detection with the same backbone. Besides, our DEA-Net which integrated with the baseline of ReDet achieves the state-of-the-art performance by 80.37 the previous best model by 1.1

READ FULL TEXT

page 1

page 4

page 10

page 11

page 13

research
02/05/2022

Investigating the Challenges of Class Imbalance and Scale Variation in Object Detection in Aerial Images

While object detection is a common problem in computer vision, it is eve...
research
12/05/2019

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

Object detection has been dominated by anchor-based detectors for severa...
research
03/21/2021

Learning Calibrated-Guidance for Object Detection in Aerial Images

Recently, the study on object detection in aerial images has made tremen...
research
09/05/2019

AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy

Colorectal cancer (CRC) is a common and lethal disease. Globally, CRC is...
research
06/28/2022

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

Tiny object detection (TOD) in aerial images is challenging since a tiny...
research
12/01/2018

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

Object detection in aerial images is an active yet challenging task in c...
research
12/11/2019

Learning from Noisy Anchors for One-stage Object Detection

State-of-the-art object detectors rely on regressing and classifying an ...

Please sign up or login with your details

Forgot password? Click here to reset