# Distilling Object Detectors with Fine-grained Feature Imitation

arXiv: https://arxiv.org/abs/1906.03609 · HTML: https://mlsanity.com/paper/1906.03609/

## Key facts

- Cited by 189 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 30 of 189)

- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Focal and Global Knowledge Distillation for Detectors](https://mlsanity.com/paper/2111.11837/) (2021)
- [General Instance Distillation for Object Detection](https://mlsanity.com/paper/2103.02340/) (2021)
- [Masked Generative Distillation](https://mlsanity.com/paper/2205.01529/) (2022)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation](https://mlsanity.com/paper/2204.02136/) (2022)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2303.05892/) (2023)
- [Object DGCNN: 3D Object Detection using Dynamic Graphs](https://mlsanity.com/paper/2110.06923/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection](https://mlsanity.com/paper/2203.14956/) (2022)
- [Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15793/) (2022)
- [PnP-DETR: Towards Efficient Visual Analysis with Transformers](https://mlsanity.com/paper/2109.07036/) (2021)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [CrossKD: Cross-Head Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2306.11369/) (2023)
- [Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation](https://mlsanity.com/paper/2202.03680/) (2022)
- [NORM: Knowledge Distillation via N-to-One Representation Matching](https://mlsanity.com/paper/2305.13803/) (2023)
- [Instance-Conditional Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2110.12724/) (2021)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient](https://mlsanity.com/paper/2207.02039/) (2022)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation](https://mlsanity.com/paper/2112.04840/) (2021)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Distilling Object Detectors with Feature Richness](https://mlsanity.com/paper/2111.00674/) (2021)
- [DAMO-YOLO : A Report on Real-Time Object Detection Design](https://mlsanity.com/paper/2211.15444/) (2022)
- [Undistillable: Making A Nasty Teacher That CANNOT teach students](https://mlsanity.com/paper/2105.07381/) (2021)
- [DETRDistill: A Universal Knowledge Distillation Framework for DETR-families](https://mlsanity.com/paper/2211.10156/) (2022)

## Abstract (arXiv)

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic cumbersome teacher model's output to get improved generalization. However, related methods mainly focus on simple task of classification while do not consider complex tasks like object detection. We show applying the vanilla knowledge distillation to detection model gets minor gain. To address the challenge of distilling knowledge in detection model, we propose a fine-grained feature imitation method exploiting the cross-location discrepancy of feature response. Our intuition is that detectors care more about local near object regions. Thus the discrepancy of feature response on the near object anchor locations reveals important information of how teacher model tends to generalize. We design a novel mechanism to estimate those locations and let student model imitate the teacher on them to get enhanced performance. We first validate the idea on a developed lightweight toy detector which carries simplest notion of current state-of-the-art anchor based detection models on challenging KITTI dataset, our method generates up to 15% boost of mAP for the student model compared to the non-imitated counterpart. We then extensively evaluate the method with Faster R-CNN model under various scenarios with common object detection benchmark of Pascal VOC and COCO, imitation alleviates up to 74% performance drop of student model compared to teacher. Codes released at https://github.com/twangnh/Distilling-Object-Detectors