Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters

• URL: http://arxiv.org/abs/2206.08509v1
• Date: Fri, 17 Jun 2022 02:01:56 GMT
• Title: Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters
• Authors: Harim Jung, Myeong-Seok Oh, Cheoljong Yang, Seong-Whan Lee
• Abstract summary: Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. Recent neural architecture search (NAS) research has demonstrated that automatically designing a backbone specifically for object detection helps improve the overall accuracy. We introduce a neural architecture adaptation method that can optimize the given backbone for detection purposes, while still allowing the use of pre-trained parameters.
• Score: 17.090405682103167
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. However, image classification and object detection are essentially different tasks and there is no guarantee that the optimal backbone for classification is also optimal for object detection. Recent neural architecture search (NAS) research has demonstrated that automatically designing a backbone specifically for object detection helps improve the overall accuracy. In this paper, we introduce a neural architecture adaptation method that can optimize the given backbone for detection purposes, while still allowing the use of pre-trained parameters. We propose to adapt both the micro- and macro-architecture by searching for specific operations and the number of layers, in addition to the output channel dimensions of each block. It is important to find the optimal channel depth, as it greatly affects the feature representation capability and computation cost. We conduct experiments with our searched backbone for object detection and demonstrate that our backbone outperforms both manually designed and searched state-of-the-art backbones on the COCO dataset.

Related papers

• The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset [120.08736654413637]
  The quality of the features extracted by the backbone architecture can have a significant impact on the overall detection performance. Our study evaluates three well-known autonomous vehicle datasets, namely KITTI, NuScenes, and BDD, to compare the performance of different backbone architectures on object detection tasks.
  arXiv  Detail & Related papers  (2023-09-15T17:32:15Z)
• Rethinking the backbone architecture for tiny object detection [0.0]
  Existing tiny object detection methods use standard deep neural networks as their backbone architecture. We argue that such backbones are inappropriate for detecting tiny objects as they are designed for the classification of larger objects, and do not have the spatial resolution to identify small targets. We design 'bottom-heavy' versions of backbones that allocate more resources to processing higher-resolution features without introducing any additional computational burden overall.
  arXiv  Detail & Related papers  (2023-03-20T16:50:29Z)
• Adaptive Rotated Convolution for Rotated Object Detection [96.94590550217718]
  We present Adaptive Rotated Convolution (ARC) module to handle rotated object detection problem. In our ARC module, the convolution kernels rotate adaptively to extract object features with varying orientations in different images. The proposed approach achieves state-of-the-art performance on the DOTA dataset with 81.77% mAP.
  arXiv  Detail & Related papers  (2023-03-14T11:53:12Z)
• 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)
• Simple Open-Vocabulary Object Detection with Vision Transformers [51.57562920090721]
  We propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection.
  arXiv  Detail & Related papers  (2022-05-12T17:20:36Z)
• GiraffeDet: A Heavy-Neck Paradigm for Object Detection [13.476168814994862]
  We propose a novel heavy-neck paradigm, GiraffeDet, for efficient object detection. GiraffeDet uses an extremely lightweight backbone and a very deep and large neck module. GiraffeDet consistently outperforms previous SOTA models across a wide spectrum of resource constraints.
  arXiv  Detail & Related papers  (2022-02-09T03:23:49Z)
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition [77.95361323613147]
  Current state-of-the-art visual recognition systems rely on pretraining a neural network on a large-scale dataset and finetuning the network weights on a smaller dataset. In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness. Our method can be easily generalized to an unsupervised paradigm by replacing supernet training with self-supervised learning in the source domain tasks and performing linear evaluation in the downstream tasks.
  arXiv  Detail & Related papers  (2021-03-31T08:15:17Z)
• CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images [0.9462808515258465]
  In this paper, we discuss the role of discriminative features in object detection. We then propose a Critical Feature Capturing Network (CFC-Net) to improve detection accuracy. We show that our method achieves superior detection performance compared with many state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-01-18T02:31:09Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)
• Adaptive Linear Span Network for Object Skeleton Detection [56.78705071830965]
  We propose adaptive linear span network (AdaLSN) to automatically configure and integrate scale-aware features for object skeleton detection. AdaLSN substantiates its versatility by achieving significantly higher accuracy and latency trade-off. It also demonstrates general applicability to image-to-mask tasks such as edge detection and road extraction.
  arXiv  Detail & Related papers  (2020-11-08T12:51:14Z)

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.