DetNAS: Backbone Search for Object Detection

By Yukang Chen, Tong Yang, X. Zhang, Gaofeng Meng, Xinyu Xiao. 2019

289 citations recorded by the source corpus.

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNet pre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection. We train the supernet under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. This framework makes NAS on backbones very efficient. In experiments, we show the effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet and the two-stage FPN. We empirically find that networks searched on object detection shows consistent superiority compared to those searched on ImageNet classification. The resulting architecture achieves superior performance than hand-crafted networks on COCO with much less FLOPs complexity.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neural Architecture Search & AutoML

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Neural Architecture Search & AutoML

Citations in the corpus

YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, background): “In addition to the above models, some researchers put their emphasis on directly building a new backbone (DetNet [43], DetNAS [7]) or a new whole model (SpineNet [12], HitDetector [20]) for object detection.”
Computation Reallocation for Object Detection (2019, methodology): “There are some work use NAS methods on object detection task (Chen et al., 2019; Ning Wang & Shen, 2019; Ghiasi et al., 2019).”
Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism (2023, background): “Single-stage detection models, especially YOLO series models, have been widely welcomed in the industry due to their simple structure and balance between speed and accuracy.”
AdaBits: Neural Network Quantization With Adaptive Bit-Widths (2019, unknown): “The NAS algorithms also benefit other tasks, such as generative adversarial networks [11], object detection [5] and segmentation [23].”
Neural Architecture Search with GBDT (2020, background): “Neural architecture search (NAS) has shown its effectiveness in automatically designing neural network architectures and been applied in many tasks such as image classiﬁcation [37, 38], object detection [6, 4], network pruning [33] and neural machine translation [22].”
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution (2020, unknown): “To tackle these, researchers have proposed different techniques to reduce the search cost, including differentiable architecture search [30], path-level binarization [6], single-path one-shot sampling [15, 8, 4], and weight sharing [50, 4, 57].”
AMER: Automatic Behavior Modeling and Interaction Exploration in Recommender System (2020, background): “Though diverse complex searching algorithms [5, 7, 10, 13] have been coupled with one-shot NAS, recent studies [4, 14, 37] reveal that the primitive random search with one-shot strategy is a surprisingly competitive baseline compared to gradient-based methods such as DARTS [44] and SNAS [76] or…”
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients (2021, methodology): “…design, with achieving remarkable success on image recognition (Tan & Le, 2019; Li et al., 2021b; 2020), language modeling (Jiang et al., 2019), and other deep learning ap-1 plications (Ren et al., 2020; Cheng et al., 2020; Chen et al., 2019b; Hu et al., 2021; Zhu et al., 2021; Ren et al., 2021).”
Imbalance Problems in Object Detection: A Review (2019, background): “[122], however it is not within the scope of our paper.”
RTMDet: An Empirical Study of Designing Real-Time Object Detectors (2022, methodology): “To improve the model efficiency, efficient backbone networks and model scaling strategies [3, 41, 71] and enhancement of multi-scale feature [7, 23, 36, 46, 49, 68] are explored either by handcrafted design or neural architecture search [10, 17, 23, 74].”