OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

  title={OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection},
  author={Tingting Liang and Yongtao Wang and Guosheng Hu and Zhi Tang and Haibin Ling},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy. Specifically, we first introduce six heterogeneous information paths to build our search space, namely top-down, bottom-up, fusing… 

Figures and Tables from this paper

Object detection with noisy annotations in high-resolution remote sensing images using robust EfficientDet

The proposed robust object detection method, called robustEfficientDet, is constructed to improve the performance of object detection in remote sensing images and can achieve better detection results with noisy annotations.

Supplementary for “EAutoDet: Efficient Architecture Search for Object Detection”

Proposition 1 is proved: convolution with weights θ ∈ RCo×( ∑M m=1 Cm)×K×K is applied on the concatenated feature X, and the input and weight matrix X̃, θ̃ is obtained.

FastDARTSDet: Fast Differentiable Architecture Joint Search on Backbone and FPN for Object Detection

This paper proposes to apply differentiable architecture search method (DARTS) to jointly search backbone and feature pyramid network (FPN) architectures for object detection task to directly search on a larger-scale object detection dataset (MS-COCO).

Rethinking the Detection Head Configuration for Traffic Object Detection

A lightweight object detection network based on matching between detection head and object distribution, termed as MHD-Net is proposed, which achieves more competitive performance than other models on BDD100K dataset and the proposed ETFOD-v2 dataset.

MRF-UNets: Searching UNet with Markov Random Fields

This work proposes Markov Random Field Neural Architecture Search (MRF-NAS) that extends and improves the recent Adaptive and Optimal Network Width Search (AOWS) method with a more general MRF framework and identifies the sub-optimality of the original UNet architecture.

FlowNAS: Neural Architecture Search for Optical Flow Estimation

A neural architecture search method named FlowNAS to automatically find the better encoder architecture for flow estimation task, and proposes Feature Alignment Distillation, which utilizes a well-trained flow estimator to guide the training of super-network.

Multi-Prior Learning via Neural Architecture Search for Blind Face Restoration

This work proposes a Face Restoration Searching Network (FRSNet) to adaptively search the suitable feature extraction architecture within the authors' specified search space, which can directly contribute to the restoration quality and designs the Multiple Facial Prior Searching network (MFPSNet) with a multi-prior learning scheme.

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

A global-to-local search scheme that exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further and an expectationguided iterative local search scheme to refine combinations effectively is proposed.

A Survey on Surrogate-assisted Efficient Neural Architecture Search

This paper begins with a brief introduction to the general framework of NAS, followed by a description of surrogate-assisted NAS, which is divided into three different categories, namely Bayesian optimization for NAS, surrogate- assisted evolutionary algorithms forNAS, and MOP for NAS.

A Survey on Computationally Efficient Neural Architecture Search

A comprehensive survey of the state-of-the-art on CE-NAS by categorizing the existing work into proxy-based and surrogate-assisted NAS methods, together with a thorough discussion of their design principles and a quantitative comparison of their performances and computational complexi-ties.



Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification

This paper proposes an architecture search framework named Auto-FPN specifically designed for detection beyond simply searching a classification backbone, and proposes two auto search modules for detection: Auto-fusion to search a better fusion of the multi-level features; Auto-head to searchA better structure for classification and bounding-box(bbox) regression.

Mask R-CNN

This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners.

The Pascal Visual Object Classes (VOC) Challenge

The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.

Single Path One-Shot Neural Architecture Search with Uniform Sampling

A Single Path One-Shot model is proposed to construct a simplified supernet, where all architectures are single paths so that weight co-adaption problem is alleviated.

Path Aggregation Network for Instance Segmentation

Path Aggregation Network (PANet) is proposed aiming at boosting information flow in proposal-based instance segmentation framework by enhancing the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation.

Feature Pyramid Networks for Object Detection

This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.

NAS-FCOS: Fast Neural Architecture Search for Object Detection

This work efficiently search for the feature pyramid network (FPN) as well as the prediction head of a simple anchor-free object detector, namely FCOS, using a tailored reinforcement learning paradigm, and is able to efficiently search a top-performing detection architecture within 4 days using 8 V100 GPUs.

Libra R-CNN: Towards Balanced Learning for Object Detection

Libra R-CNN is proposed, a simple but effective framework towards balanced learning for object detection that integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level.

Res2Net: A New Multi-Scale Backbone Architecture

This paper proposes a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block that represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.

SP-NAS: Serial-to-Parallel Backbone Search for Object Detection

This paper proposes a two-phase serial-to-parallel architecture search framework named SP-NAS towards a flexible task-oriented detection backbone that efficiently search a detection backbone by exploring a network morphism strategy on multiple detection benchmarks.