NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

By Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le. 2019

1,781 citations recorded by the source corpus.

Current state-of-the-art convolutional architectures for object detection are manually designed. Here we aim to learn a better architecture of feature pyramid network for object detection. We adopt Neural Architecture Search and discover a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections. The discovered architecture, named NAS-FPN, consists of a combination of top-down and bottom-up connections to fuse features across scales. NAS-FPN, combined with various backbone models in the RetinaNet framework, achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models. NAS-FPN improves mobile detection accuracy by 2 AP compared to state-of-the-art SSDLite with MobileNetV2 model in [32] and achieves 48.3 AP which surpasses Mask R-CNN [10] detection accuracy with less computation time.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

Citations in the corpus

GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding (2020, background): “For computer vision, increasing the model capacity has led to better image classification and detection accuracy for various computer vision architectures [7, 8, 9].”
Attention Augmented Convolutional Networks (2019, background): “As such, it would be interesting to see if using Attention Augmentation as a primitive in automated architecture search procedures proves useful to find even better models than those previously found in image classification [55], object detection [12], image segmentation [6] and other domains[5, 1, ”
Deformable DETR: Deformable Transformers for End-to-End Object Detection (2020, methodology): “Recently, NAS-FPN (Ghiasi et al., 2019) and Auto-FPN (Xu et al., 2019) are proposed to automatically design cross-scale connections via neural architecture search.”
AutoML: A Survey of the State-of-the-Art (2019, neutral): “Besides, some works are proposed to solve the task of object detection [141] and semantic segmentation [142], [143].”
A Comprehensive Survey of Neural Architecture Search (2020, methodology): “With the improvement of NAS search efficiency, NAS is also quickly applied in the fields of object detection [65, 75, 111, 118], semantic segmentation [63, 64, 120], adversarial learning [53], architectural scaling [114, 122, 124], multi-objective optimization [39, 115, 125], platform-aware [28, 34,”
Are Labels Necessary for Neural Architecture Search? (2020, background): “There are special focuses on reducing the overall time cost of the search process [19,24,20], or on extending to a larger variety of tasks [4,18,11,28].”
Semi-Supervised Neural Architecture Search (2020, methodology): “Neural architecture search (NAS) for automatic architecture design has been successfully applied in several tasks including image classification and language modeling [42, 26, 6].”
EfficientDet: Scalable and Efficient Object Detection (2019, methodology): “Recently, NAS-FPN [5] employs neural architecture search to search for better cross-scale feature network topology, but it requires thousands of GPU hours during search and the found network is irregular and difﬁcult to interpret or modify, as shown in Figure 2(c).”
Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising (2019, methodology): “Architectures automatically found by algorithms have achieved highly competitive performance in high-level vision tasks such as image classification [46], object detection [8, 36] and semantic segmentation [17, 29].”
DARTS+: Improved Differentiable Architecture Search with Early Stopping (2019, methodology): “The neural architectures searched by NAS have achieved the state-of-the-art results over handcrafted neural architectures in various tasks, including object classiﬁcation [4, 20, 21, 25, 26, 40], object detection [7, 36], semantic segmentation [19], recommender systems [14], etc.”
DetNAS: Backbone Search for Object Detection (2019, background): “Recently, a NAS work on object detection, NAS-FPN [5], is proposed.”
Evaluating the Search Phase of Neural Architecture Search (2019, methodology): “…optimiziation (Zhou et al., 2019) and performance predictors (Luo et al., 2018); 2) Exploiting NAS for other applications, e.g., object detection (Ghiasi et al., 2019; Chen et al., 2019), semantic segmentation (Liu et al., 2019a), and ﬁnding compact networks (Cai et al., 2018b; Wu et al., 2018;…”
Auto-Keras: An Efficient Neural Architecture Search System (2018, neutral): “, image segmentation [28], object detection [16, 32], network analysis [20, 43].”
Bottleneck Transformers for Visual Recognition (2021, methodology): “We consider the simplest and most widely used setting: ResNet-50 6 backbone with FPN 7 .”