paper-with-me

홈 › Papers

A Simple and Generic Framework for Feature Distillation via Channel-wise Transformation

2023-03-23 · Ziwei Liu, Yongtao Wang, Xiaojie Chu

Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may enforce overly strict constraints on the student thus degrade the performance of the student model. To alleviate the above feature misalignment issue, existing works mainly focus on spatially aligning the feature maps of the teacher and the student, with pixel-wise transformation. In this paper, we newly find that aligning the feature maps between teacher and student along the channel-wise dimension is also effective for addressing the feature misalignment issue. Specifically, we propose a learnable nonlinear channel-wise transformation to align the features of the student and the teacher model. Based on it, we further propose a simple and generic framework for feature distillation, with only one hyper-parameter to balance the distillation loss and the task specific loss. Extensive experimental results show that our method achieves significant performance improvements in various computer vision tasks including image classification (+3.28% top-1 accuracy for MobileNetV1 on ImageNet-1K), object detection (+3.9% bbox mAP for ResNet50-based Faster-RCNN on MS COCO), instance segmentation (+2.8% Mask mAP for ResNet50-based Mask-RCNN), and semantic segmentation (+4.66% mIoU for ResNet18-based PSPNet in semantic segmentation on Cityscapes), which demonstrates the effectiveness and the versatility of the proposed method. The code will be made publicly available.

📄 PDF Abstract BibTeX arXiv:2303.13212

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationInstance SegmentationKnowledge Distillationobject-detectionObject DetectionSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Auxiliary Classifier Auxiliary Classifiers are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the…
Average Pooling 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Batch Normalization 설명 없음
Dilated Convolution 설명 없음
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Similar Papers 제목 키워드 기반

Distilling Channels for Efficient Deep Tracking

2024-09-18 · Shiming Ge, Zhao Luo, Chunhui Zhang, Yingying Hua 외

Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep net…

Feature CompressionVisual Tracking

AMD: Adaptive Masked Distillation for Object Detection

2023-01-31 · Guang Yang, Yin Tang, Jun Li, Jianhua Xu 외

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective f…

Knowledge DistillationModel CompressionObjectobject-detection+1

Channel-wise Knowledge Distillation for Dense Prediction

2020-11-26 · ICCV 2021 10 · Changyong Shu, Yifan Liu, Jianfei Gao, Zheng Yan 외

Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and teacher networks' feature maps in the spa…

Knowledge DistillationPredictionSegmentationSemantic Segmentation

Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers

2025-11-10 · Huiyuan Tian, Bonan Xu, Shijian Li arxiv

While feature-based knowledge distillation has proven highly effective for compressing CNNs, these techniques unexpectedly fail when applied to Vision Transformers (ViTs), often performing worse than simple logit-based d…

Knowledge Distillation

Semantic-Guided Feature Distillation for Multimodal Recommendation

2023-08-06 · Fan Liu, Huilin Chen, Zhiyong Cheng, Liqiang Nie 외

Multimodal recommendation exploits the rich multimodal information associated with users or items to enhance the representation learning for better performance. In these methods, end-to-end feature extractors (e.g., shal…

Multimodal RecommendationRepresentation Learning