Scale-aware Automatic Augmentation for Object Detection
- URL: http://arxiv.org/abs/2103.17220v1
- Date: Wed, 31 Mar 2021 17:11:14 GMT
- Title: Scale-aware Automatic Augmentation for Object Detection
- Authors: Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei Li, Jiaya
Jia
- Abstract summary: We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
In experiments, Scale-aware AutoAug yields significant and consistent improvement on various object detectors.
- Score: 63.087930708444695
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose Scale-aware AutoAug to learn data augmentation policies for object
detection. We define a new scale-aware search space, where both image- and
box-level augmentations are designed for maintaining scale invariance. Upon
this search space, we propose a new search metric, termed Pareto Scale Balance,
to facilitate search with high efficiency. In experiments, Scale-aware AutoAug
yields significant and consistent improvement on various object detectors
(e.g., RetinaNet, Faster R-CNN, Mask R-CNN, and FCOS), even compared with
strong multi-scale training baselines. Our searched augmentation policies are
transferable to other datasets and box-level tasks beyond object detection
(e.g., instance segmentation and keypoint estimation) to improve performance.
The search cost is much less than previous automated augmentation approaches
for object detection. It is notable that our searched policies have meaningful
patterns, which intuitively provide valuable insight for human data
augmentation design. Code and models will be available at
https://github.com/Jia-Research-Lab/SA-AutoAug.
Related papers
- SalienDet: A Saliency-based Feature Enhancement Algorithm for Object
Detection for Autonomous Driving [160.57870373052577]
We propose a saliency-based OD algorithm (SalienDet) to detect unknown objects.
Our SalienDet utilizes a saliency-based algorithm to enhance image features for object proposal generation.
We design a dataset relabeling approach to differentiate the unknown objects from all objects in training sample set to achieve Open-World Detection.
arXiv Detail & Related papers (2023-05-11T16:19:44Z) - Multi-Objective Evolutionary for Object Detection Mobile Architectures
Search [21.14296703753317]
We propose a mobile object detection backbone network architecture search algorithm based on non-dominated sorting for NAS scenarios.
The proposed approach can search the backbone networks with different depths, widths, or expansion sizes via a technique of weight mapping.
Under similar computational complexity, the accuracy of the backbone network architecture we search for is 2.0% mAP higher than MobileDet.
arXiv Detail & Related papers (2022-11-05T00:28:49Z) - LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations [55.45435708426761]
LidarAugment is a search-based data augmentation strategy for 3D object detection.
We show LidarAugment can be customized for different model architectures.
It consistently improves convolution-based UPillars/StarNet/RSN and transformer-based SWFormer.
arXiv Detail & Related papers (2022-10-24T18:00:04Z) - Scaling Novel Object Detection with Weakly Supervised Detection
Transformers [21.219817483091166]
We propose the Weakly Supervised Detection Transformer, which enables efficient knowledge transfer from a large-scale pretraining dataset to WSOD finetuning.
Our experiments show that our approach outperforms previous state-of-the-art models on large-scale novel object detection datasets.
arXiv Detail & Related papers (2022-07-11T21:45:54Z) - Category-Aware Transformer Network for Better Human-Object Interaction
Detection [20.857034771924997]
We study the issue of promoting transformer-based HOI detectors by initializing the Object Query with category-aware semantic information.
Specifically, the Object Query would be represented via category priors represented by an external object detection model to yield better performance.
A HOI detection model equipped with our idea outperforms the baseline by a large margin to achieve a new state-of-the-art result.
arXiv Detail & Related papers (2022-04-11T07:21:24Z) - Web-Scale Generic Object Detection at Microsoft Bing [4.350999432264304]
We present Generic Object Detection (GenOD), one of the largest object detection systems deployed to a web-scale general visual search engine.
It can detect over 900 categories for all Microsoft Bing Visual Search queries in near real-time.
arXiv Detail & Related papers (2021-07-05T06:46:09Z) - Robust and Accurate Object Detection via Adversarial Learning [111.36192453882195]
This work augments the fine-tuning stage for object detectors by exploring adversarial examples.
Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the object detection benchmark.
arXiv Detail & Related papers (2021-03-23T19:45:26Z) - DecAug: Augmenting HOI Detection via Decomposition [54.65572599920679]
Current algorithms suffer from insufficient training samples and category imbalance within datasets.
We propose an efficient and effective data augmentation method called DecAug for HOI detection.
Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset.
arXiv Detail & Related papers (2020-10-02T13:59:05Z) - AutoOD: Automated Outlier Detection via Curiosity-guided Search and
Self-imitation Learning [72.99415402575886]
Outlier detection is an important data mining task with numerous practical applications.
We propose AutoOD, an automated outlier detection framework, which aims to search for an optimal neural network model.
Experimental results on various real-world benchmark datasets demonstrate that the deep model identified by AutoOD achieves the best performance.
arXiv Detail & Related papers (2020-06-19T18:57:51Z)
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.