# Scale-Invariant Object Detection by Adaptive Convolution with Unified Global-Local Context

arXiv: https://arxiv.org/abs/2410.05274 · HTML: https://mlsanity.com/paper/2410.05274/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 17 Sep 2024.

## Builds on (most cited first, 27 of 27)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution](https://mlsanity.com/paper/2006.02334/) (2020)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [Deep Colorization](https://mlsanity.com/paper/1605.00075/) (2016)
- [Deep Gradient Learning for Efficient Camouflaged Object Detection](https://mlsanity.com/paper/2205.12853/) (2022)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Robust and Accurate Object Detection via Adversarial Learning](https://mlsanity.com/paper/2103.13886/) (2021)
- [MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection](https://mlsanity.com/paper/2009.11528/) (2020)
- [The Box Size Confidence Bias Harms Your Object Detector](https://mlsanity.com/paper/2112.01901/) (2021)
- [Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection](https://mlsanity.com/paper/2207.12042/) (2022)
- [Task Specific Attention is one more thing you need for object detection](https://mlsanity.com/paper/2202.09048/) (2022)

## Abstract (arXiv)

Dense features are important for detecting minute objects in images. Unfortunately, despite the remarkable efficacy of the CNN models in multi-scale object detection, CNN models often fail to detect smaller objects in images due to the loss of dense features during the pooling process. Atrous convolution addresses this issue by applying sparse kernels. However, sparse kernels often can lose the multi-scale detection efficacy of the CNN model. In this paper, we propose an object detection model using a Switchable (adaptive) Atrous Convolutional Network (SAC-Net) based on the efficientDet model. A fixed atrous rate limits the performance of the CNN models in the convolutional layers. To overcome this limitation, we introduce a switchable mechanism that allows for dynamically adjusting the atrous rate during the forward pass. The proposed SAC-Net encapsulates the benefits of both low-level and high-level features to achieve improved performance on multi-scale object detection tasks, without losing the dense features. Further, we apply a depth-wise switchable atrous rate to the proposed network, to improve the scale-invariant features. Finally, we apply global context on the proposed model. Our extensive experiments on benchmark datasets demonstrate that the proposed SAC-Net outperforms the state-of-the-art models by a significant margin in terms of accuracy.