paper-with-me

Papers

Instance-Conditional Knowledge Distillation for Object Detection

2021-10-25 · NeurIPS 2021 12 · Zijian Kang, Peizhen Zhang, Xiangyu Zhang, Jian Sun, Nanning Zheng

Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection targets, making the distillation hard to balance. In this paper, we propose a conditional distillation framework to distill the desired knowledge, namely knowledge that is beneficial in terms of both classification and localization for every instance. The framework introduces a learnable conditional decoding module, which retrieves information given each target instance as query. Specifically, we encode the condition information as query and use the teacher's representations as key. The attention between query and key is used to measure the contribution of different features, guided by a localization-recognition-sensitive auxiliary task. Extensive experiments demonstrate the efficacy of our method: we observe impressive improvements under various settings. Notably, we boost RetinaNet with ResNet-50 backbone from 37.4 to 40.7 mAP (+3.3) under 1x schedule, that even surpasses the teacher (40.4 mAP) with ResNet-101 backbone under 3x schedule. Code has been released on https://github.com/megvii-research/ICD.

📄 PDF Abstract BibTeX arXiv:2110.12724

Code (1)

megvii-research/ICD 공식 구현 pytorch

Tasks

Image ClassificationKnowledge DistillationObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

FPN 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Focal Loss A Focal Loss function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to…
RetinaNet RetinaNet is a one-stage object detection model that utilizes a focal loss function to address class imbalance during training.…

Similar Papers 제목 키워드 기반

Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective

2022-08-26 · Jiangmeng Li, Yanan Zhang, Wenwen Qiang, Lingyu Si 외

Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification, object detection, etc. However, few-sh…

Few-Shot LearningFew-Shot Object Detectionimage-classificationImage Classification+4

Dual Relation Knowledge Distillation for Object Detection

2023-02-11 · ZhenLiang Ni, Fukui Yang, Shengzhao Wen, Gang Zhang

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation pe…

Knowledge DistillationModel CompressionObjectobject-detection+2

Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation

2022-03-20 · CVPR 2022 1 · Zongyang Ma, Guan Luo, Jin Gao, Liang Li 외

Open-vocabulary object detection aims to detect novel object categories beyond the training set. The advanced open-vocabulary two-stage detectors employ instance-level visual-to-visual knowledge distillation to align the…

Knowledge DistillationLanguage ModellingObjectobject-detection+3

General Instance Distillation for Object Detection

2021-03-03 · CVPR 2021 1 · Xing Dai, Zeren Jiang, Zhao Wu, Yiping Bao 외

In recent years, knowledge distillation has been proved to be an effective solution for model compression. This approach can make lightweight student models acquire the knowledge extracted from cumbersome teacher models.…

Knowledge DistillationModel CompressionObjectobject-detection+2

Adaptive Instance Distillation for Object Detection in Autonomous Driving

2022-01-26 · Qizhen Lan, Qing Tian

In recent years, knowledge distillation (KD) has been widely used to derive efficient models. Through imitating a large teacher model, a lightweight student model can achieve comparable performance with more efficiency. …

Autonomous DrivingKnowledge Distillationobject-detectionObject Detection