# Scale-Aware Trident Networks for Object Detection

arXiv: https://arxiv.org/abs/1901.01892 · HTML: https://mlsanity.com/paper/1901.01892/

## Key facts

- Cited by 159 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2019.

## Built on by (most cited first, 30 of 159)

- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://mlsanity.com/paper/2112.06375/) (2021)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [UIU-Net: U-Net in U-Net for Infrared Small Object Detection](https://mlsanity.com/paper/2212.00968/) (2022)
- [Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization](https://mlsanity.com/paper/2210.14457/) (2022)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [AdaMixer: A Fast-Converging Query-Based Object Detector](https://mlsanity.com/paper/2203.16507/) (2022)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark](https://mlsanity.com/paper/2206.13996/) (2022)
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/2305.04925/) (2023)
- [A Normalized Gaussian Wasserstein Distance for Tiny Object Detection](https://mlsanity.com/paper/2110.13389/) (2021)
- [Multi-Modal Classifiers for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.05493/) (2023)
- [RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2208.08738/) (2022)
- [ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes](https://mlsanity.com/paper/2106.02740/) (2021)
- [Cross-Modality Attentive Feature Fusion for Object Detection in Multispectral Remote Sensing Imagery](https://mlsanity.com/paper/2112.02991/) (2021)
- [Parsing Table Structures in the Wild](https://mlsanity.com/paper/2109.02199/) (2021)
- [Label, Verify, Correct: A Simple Few Shot Object Detection Method](https://mlsanity.com/paper/2112.05749/) (2021)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [Injecting Semantic Concepts into End-to-End Image Captioning](https://mlsanity.com/paper/2112.05230/) (2021)
- [StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training](https://mlsanity.com/paper/2303.00289/) (2023)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [Dense Learning based Semi-Supervised Object Detection](https://mlsanity.com/paper/2204.07300/) (2022)
- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)

## Abstract (arXiv)

Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.