paper-with-me

Papers

CrossKD: Cross-Head Knowledge Distillation for Object Detection

2023-06-20 · CVPR 2024 1 · Jiabao Wang, Yuming Chen, Zhaohui Zheng, Xiang Li, Ming-Ming Cheng, Qibin Hou

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this paper, we present a general and effective prediction mimicking distillation scheme, called CrossKD, which delivers the intermediate features of the student's detection head to the teacher's detection head. The resulting cross-head predictions are then forced to mimic the teacher's predictions. This manner relieves the student's head from receiving contradictory supervision signals from the annotations and the teacher's predictions, greatly improving the student's detection performance. Moreover, as mimicking the teacher's predictions is the target of KD, CrossKD offers more task-oriented information in contrast with feature imitation. On MS COCO, with only prediction mimicking losses applied, our CrossKD boosts the average precision of GFL ResNet-50 with 1x training schedule from 40.2 to 43.7, outperforming all existing KD methods. In addition, our method also works well when distilling detectors with heterogeneous backbones. Code is available at https://github.com/jbwang1997/CrossKD.

📄 PDF Abstract BibTeX arXiv:2306.11369

Code (1)

jbwang1997/crosskd 공식 구현 pytorch

Tasks

Dense Object DetectionKnowledge DistillationModel CompressionObjectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Cross-Architecture Distillation Made Simple with Redundancy Suppression

2025-07-29 · Weijia Zhang, Yuehao Liu, Wu Ran, Chao Ma arxiv

We describe a simple method for cross-architecture knowledge distillation, where the knowledge transfer is cast into a redundant information suppression formulation. Existing methods introduce sophisticated modules, arch…

Knowledge Distillation

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

2026-03-22 · Yupeng Zhang, Ruize Han, Zhiwei Chen, Wei Feng 외 arxiv

Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-categ…

Knowledge DistillationObject Detection

UniKD: Universal Knowledge Distillation for Mimicking Homogeneous or Heterogeneous Object Detectors

2023-01-01 · ICCV 2023 1 · Shanshan Lao, Guanglu Song, Boxiao Liu, Yu Liu 외

Knowledge distillation (KD) has become a standard method to boost the performance of lightweight object detectors. Most previous works are feature-based, where students mimic the features of homogeneous teacher detec…

Knowledge Distillation

Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation

2022-04-05 · CVPR 2022 1 · Tao Feng, Mang Wang, Hangjie Yuan

Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a…

Class-Incremental Object DetectionIncremental LearningKnowledge Distillationobject-detection+1

FD-CanKD: Frequency-Decoupled Cross-Attention Distillation as a Refinement Prior for Compact Object Detectors

2026-08-19 · YoungJae Cheong, Jhonghyun An arxiv

Compact object detectors are suitable for resource-constrained visual perception, but their limited representation capacity creates an accuracy gap relative to large models. Conventional detector distillation often relie…

Knowledge Distillation