# DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection

arXiv: https://arxiv.org/abs/1412.5661 · HTML: https://mlsanity.com/paper/1412.5661/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2014.

## Built on by (most cited first, 19 of 19)

- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [Occlusion Handling in Generic Object Detection: A Review](https://mlsanity.com/paper/2101.08845/) (2021)
- [Semi-TCL: Semi-Supervised Track Contrastive Representation Learning](https://mlsanity.com/paper/2107.02396/) (2021)
- [CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement](https://mlsanity.com/paper/2403.10362/) (2024)
- [Improved YOLOv5 network for real-time multi-scale traffic sign detection](https://mlsanity.com/paper/2112.08782/) (2021)
- [Robots Autonomously Detecting People: A Multimodal Deep Contrastive Learning Method Robust to Intraclass Variations](https://mlsanity.com/paper/2203.00187/) (2022)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Reconstruct Face from Features Using GAN Generator as a Distribution Constraint](https://mlsanity.com/paper/2206.04295/) (2022)
- [High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection](https://mlsanity.com/paper/2304.03812/) (2023)
- [Mitigating Domain Mismatch in Face Recognition Using Style Matching](https://mlsanity.com/paper/2102.13327/) (2021)
- [Pre-Trained Language Transformers are Universal Image Classifiers](https://mlsanity.com/paper/2201.10182/) (2022)
- [PredCoin: Defense against Query-based Hard-label Attack](https://mlsanity.com/paper/2102.02923/) (2021)
- [A Generic Object Re-identification System for Short Videos](https://mlsanity.com/paper/2102.05275/) (2021)
- [Self-Reorganizing and Rejuvenating CNNs for Increasing Model Capacity Utilization](https://mlsanity.com/paper/2102.06870/) (2021)
- [Autonomous Navigation in Dynamic Environments: Deep Learning-Based Approach](https://mlsanity.com/paper/2102.08758/) (2021)
- [Content-adaptive Representation Learning for Fast Image Super-resolution](https://mlsanity.com/paper/2105.09645/) (2021)
- [Deep Learning-based Spatio Temporal Facial Feature Visual Speech Recognition](https://mlsanity.com/paper/2305.00552/) (2023)
- [Age-Invariant Face Embedding using the Wasserstein Distance](https://mlsanity.com/paper/2305.02745/) (2023)

## Abstract (arXiv)

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN citegirshick2014rich, which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provide a global view for people to understand the deep learning object detection pipeline.