Fewer is More: Efficient Object Detection in Large Aerial Images
- URL: http://arxiv.org/abs/2212.13136v1
- Date: Mon, 26 Dec 2022 12:49:47 GMT
- Title: Fewer is More: Efficient Object Detection in Large Aerial Images
- Authors: Xingxing Xie, Gong Cheng, Qingyang Li, Shicheng Miao, Ke Li, Junwei
Han
- Abstract summary: This paper presents an Objectness Activation Network (OAN) to help detectors focus on fewer patches but achieve more efficient inference and more accurate results.
Using OAN, all five detectors acquire more than 30.0% speed-up on three large-scale aerial image datasets.
We extend our OAN to driving-scene object detection and 4K video object detection, boosting the detection speed by 112.1% and 75.0%, respectively.
- Score: 59.683235514193505
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Current mainstream object detection methods for large aerial images usually
divide large images into patches and then exhaustively detect the objects of
interest on all patches, no matter whether there exist objects or not. This
paradigm, although effective, is inefficient because the detectors have to go
through all patches, severely hindering the inference speed. This paper
presents an Objectness Activation Network (OAN) to help detectors focus on
fewer patches but achieve more efficient inference and more accurate results,
enabling a simple and effective solution to object detection in large images.
In brief, OAN is a light fully-convolutional network for judging whether each
patch contains objects or not, which can be easily integrated into many object
detectors and jointly trained with them end-to-end. We extensively evaluate our
OAN with five advanced detectors. Using OAN, all five detectors acquire more
than 30.0% speed-up on three large-scale aerial image datasets, meanwhile with
consistent accuracy improvements. On extremely large Gaofen-2 images
(29200$\times$27620 pixels), our OAN improves the detection speed by 70.5%.
Moreover, we extend our OAN to driving-scene object detection and 4K video
object detection, boosting the detection speed by 112.1% and 75.0%,
respectively, without sacrificing the accuracy. Code is available at
https://github.com/Ranchosky/OAN.
Related papers
- ESOD: Efficient Small Object Detection on High-Resolution Images [36.80623357577051]
Small objects are usually sparsely distributed and locally clustered.
Massive feature extraction computations are wasted on the non-target background area of images.
We propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing.
arXiv Detail & Related papers (2024-07-23T12:21:23Z) - SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection [59.868772767818975]
We propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++.
Specifically, we observe that objects from aerial images are usually arbitrary orientations, small scales, and aggregation.
Extensive experiments conducted on various multi-oriented object datasets under various labeled settings demonstrate the effectiveness of our method.
arXiv Detail & Related papers (2024-07-01T07:03:51Z) - Learned Two-Plane Perspective Prior based Image Resampling for Efficient
Object Detection [20.886999159134138]
Real-time efficient perception is critical for autonomous navigation and city scale sensing.
In this work, we propose a learnable geometry-guided prior that incorporates rough geometry of the 3D scene.
Our approach improves detection rate by +4.1 $AP_S$ or +39% and in real-time performance by +5.3 $sAP_S$ or +63% for small objects over state-of-the-art (SOTA)
arXiv Detail & Related papers (2023-03-25T00:43:44Z) - EAutoDet: Efficient Architecture Search for Object Detection [110.99532343155073]
EAutoDet framework can discover practical backbone and FPN architectures for object detection in 1.4 GPU-days.
We propose a kernel reusing technique by sharing the weights of candidate operations on one edge and consolidating them into one convolution.
In particular, the discovered architectures surpass state-of-the-art object detection NAS methods and achieve 40.1 mAP with 120 FPS and 49.2 mAP with 41.3 FPS on COCO test-dev set.
arXiv Detail & Related papers (2022-03-21T05:56:12Z) - Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection [2.578242050187029]
Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection.
Proposed technique has been integrated with Detectron2, MMDetection and YOLOv5 models.
arXiv Detail & Related papers (2022-02-14T18:49:12Z) - Remote Sensing Image Super-resolution and Object Detection: Benchmark
and State of the Art [7.74389937337756]
This paper reviews current datasets and object detection methods (deep learning-based) for remote sensing images.
We propose a large-scale, publicly available benchmark Remote Sensing Super-resolution Object Detection dataset.
We also propose a novel Multi-class Cyclic super-resolution Generative adversarial network with Residual feature aggregation (MCGR) and auxiliary YOLOv5 detector to benchmark image super-resolution-based object detection.
arXiv Detail & Related papers (2021-11-05T04:56:34Z) - NAS-FCOS: Efficient Search for Object Detection Architectures [113.47766862146389]
We propose an efficient method to obtain better object detectors by searching for the feature pyramid network (FPN) and the prediction head of a simple anchor-free object detector.
With carefully designed search space, search algorithms, and strategies for evaluating network quality, we are able to find top-performing detection architectures within 4 days using 8 V100 GPUs.
arXiv Detail & Related papers (2021-10-24T12:20:04Z) - A Light-Weight Object Detection Framework with FPA Module for Optical
Remote Sensing Imagery [12.762588615997624]
We propose an efficient anchor free object detector, CenterFPANet.
To pursue speed, we use a lightweight backbone and introduce the asymmetric revolution block.
This strategy can improve the accuracy of remote sensing image object detection without reducing the detection speed.
arXiv Detail & Related papers (2020-09-07T12:41:17Z) - Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture.
We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions.
Results show our method's effectiveness in detecting small-scaled pedestrians.
arXiv Detail & Related papers (2020-08-19T13:13:01Z) - NETNet: Neighbor Erasing and Transferring Network for Better Single Shot
Object Detection [170.30694322460045]
We propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features.
A single-shot network called NETNet is constructed for scale-aware object detection.
arXiv Detail & Related papers (2020-01-18T15:21:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.