paper-with-me

홈 › Papers

ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector

2023-01-01 · CVPR 2023 1 · Yichen Zhu, Qiqi Zhou, Ning Liu, Zhiyuan Xu, Zhicai Ou, Xiaofeng Mou, Jian Tang

Despite the prominent success of general object detection, the performance and efficiency of Small Object Detection (SOD) are still unsatisfactory. Unlike existing works that struggle to balance the trade-off between inference speed and SOD performance, in this paper, we propose a novel Scale-aware Knowledge Distillation (ScaleKD), which transfers knowledge of a complex teacher model to a compact student model. We design two novel modules to boost the quality of knowledge transfer in distillation for SOD: 1) a scale-decoupled feature distillation module that disentangled teacher's feature representation into multi-scale embedding that enables explicit feature mimicking of the student model on small objects. 2) a cross-scale assistant to refine the noisy and uninformative bounding boxes prediction student models, which can mislead the student model and impair the efficacy of knowledge distillation. A multi-scale cross-attention layer is established to capture the multi-scale semantic information to improve the student model. We conduct experiments on COCO and VisDrone datasets with diverse types of models, i.e., two-stage and one-stage detectors, to evaluate our proposed method. Our ScaleKD achieves superior performance on general detection performance and obtains spectacular improvement regarding the SOD performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillationobject-detectionObject DetectionSmall Object DetectionTransfer Learning

Methods 이 논문이 사용한 방법론

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.…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

ScaleKD: Strong Vision Transformers Could Be Excellent Teachers

2024-11-11 · Jiawei Fan, Chao Li, Xiaolong Liu, Anbang Yao

In this paper, we question if well pre-trained vision transformer (ViT) models could be used as teachers that exhibit scalable properties to advance cross architecture knowledge distillation (KD) research, in the context…

image-classificationImage ClassificationKnowledge Distillation

Distilling Word Embeddings: An Encoding Approach

2015-06-15 · Lili Mou, Ran Jia, Yan Xu, Ge Li 외

Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restr…

Word Embeddings

Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation

2020-03-05 · WS 2020 7 · Mitchell A. Gordon, Kevin Duh

We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillati…

Domain AdaptationKnowledge DistillationMachine TranslationTranslation

Graph-based Knowledge Distillation by Multi-head Attention Network

2019-07-04 · Seunghyun Lee, Byung Cheol Song

Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN.…

Inductive BiasKnowledge DistillationMulti-Task LearningTransfer Learning

Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models

2023-11-15 · Weize Liu, Guocong Li, Kai Zhang, Bang Du 외

Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their…

Transfer Learning