# Object Detection Networks on Convolutional Feature Maps

arXiv: https://arxiv.org/abs/1504.06066 · HTML: https://mlsanity.com/paper/1504.06066/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2015.

## Built on by (most cited first, 17 of 17)

- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [SiMaN: Sign-to-Magnitude Network Binarization](https://mlsanity.com/paper/2102.07981/) (2021)
- [Towards Accurate and Compact Architectures via Neural Architecture Transformer](https://mlsanity.com/paper/2102.10301/) (2021)
- [Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales](https://mlsanity.com/paper/2106.06418/) (2021)
- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [Removing Human Bottlenecks in Bird Classification Using Camera Trap Images and Deep Learning](https://mlsanity.com/paper/2305.02097/) (2023)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Bi-fidelity Evolutionary Multiobjective Search for Adversarially Robust Deep Neural Architectures](https://mlsanity.com/paper/2207.05321/) (2022)
- [Empowering Wildlife Guardians: An Equitable Digital Stewardship and Reward System for Biodiversity Conservation using Deep Learning and 3/4G Camera Traps](https://mlsanity.com/paper/2304.12703/) (2023)
- [A Multicore and Edge TPU-Accelerated Multimodal TinyML System for Livestock Behavior Recognition](https://mlsanity.com/paper/2504.11467/) (2025)
- [CV 3315 Is All You Need : Semantic Segmentation Competition](https://mlsanity.com/paper/2206.12571/) (2022)
- [Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery](https://mlsanity.com/paper/2503.19202/) (2025)
- [Frequency Regularization: Restricting Information Redundancy of Convolutional Neural Networks](https://mlsanity.com/paper/2304.07973/) (2023)
- [Machine-Learning enabled analysis of ELM filament dynamics in KSTAR](https://mlsanity.com/paper/2201.07941/) (2022)
- [Self-Balanced R-CNN for Instance Segmentation](https://mlsanity.com/paper/2404.16633/) (2024)
- [A Real-time Multimodal Transformer Neural Network-powered Wildfire Forecasting System](https://mlsanity.com/paper/2503.05971/) (2025)

## Abstract (arXiv)

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important. We experiment with region-wise classifier networks that use shared, region-independent convolutional features. We call them "Networks on Convolutional feature maps" (NoCs). We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier. We show by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015.