Efficient Crowd Counting via Structured Knowledge Transfer

by   Lingbo Liu, et al.

Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications. However, most previous works relied on heavy backbone networks and required prohibitive runtimes, which would seriously restrict their deployment scopes and cause poor scalability. To liberate these crowd counting models, we propose a novel Structured Knowledge Transfer (SKT) framework integrating two complementary transfer modules, which can generate a lightweight but still highly effective student network by fully exploiting the structured knowledge of a well-trained teacher network. Specifically, an Intra-Layer Pattern Transfer sequentially distills the knowledge embedded in single-layer features of the teacher network to guide feature learning of the student network. Simultaneously, an Inter-Layer Relation Transfer densely distills the cross-layer correlation knowledge of the teacher to regularize the student's feature evolution. In this way, our student network can learn compact and knowledgeable features, yielding high efficiency and competitive performance. Extensive evaluations on three benchmarks well demonstrate the knowledge transfer effectiveness of our SKT for extensive crowd counting models. In particular, only having one-sixteenth of the parameters and computation cost of original models, our distilled VGG-based models obtain at least 6.5× speed-up on an Nvidia 1080 GPU and even achieve state-of-the-art performance.


page 3

page 4

page 7


Crowd Counting with Online Knowledge Learning

Efficient crowd counting models are urgently required for the applicatio...

Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting

The lightweight crowd counting models, in particular knowledge distillat...

Network-Agnostic Knowledge Transfer for Medical Image Segmentation

Conventional transfer learning leverages weights of pre-trained networks...

Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer

Unsupervised crowd counting is a challenging yet not largely explored ta...

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

Semi-supervised approaches for crowd counting attract attention, as the ...

Real-Time Correlation Tracking via Joint Model Compression and Transfer

Correlation filters (CF) have received considerable attention in visual ...

Learning from Higher-Layer Feature Visualizations

Driven by the goal to enable sleep apnea monitoring and machine learning...

Code Repositories


SKT distillation (ACM MM 2020)

view repo


Efficient Crowd Counting via Structured Knowledge Transfer (SKT, ACM MM 2020)

view repo



view repo

Please sign up or login with your details

Forgot password? Click here to reset