CVMar 23, 2020

Efficient Crowd Counting via Structured Knowledge Transfer

arXiv:2003.10120v377 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses the deployment and scalability issues in crowd counting for real-world applications by making models more efficient.

The paper tackles the problem of inefficient crowd counting models by proposing a Structured Knowledge Transfer (SKT) framework, which distills knowledge from a teacher network to create a lightweight student network that achieves at least 6.5× speed-up and state-of-the-art performance using only around 6% of parameters and computation cost.

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 run-time consumption, 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, which fully exploits the structured knowledge of a well-trained teacher network to generate a lightweight but still highly effective student network. Specifically, it is integrated with two complementary transfer modules, including an Intra-Layer Pattern Transfer which sequentially distills the knowledge embedded in layer-wise features of the teacher network to guide feature learning of the student network and an Inter-Layer Relation Transfer which densely distills the cross-layer correlation knowledge of the teacher to regularize the student's feature evolutio Consequently, our student network can derive the layer-wise and cross-layer knowledge from the teacher network to learn compact yet effective features. Extensive evaluations on three benchmarks well demonstrate the effectiveness of our SKT for extensive crowd counting models. In particular, only using around $6\%$ of the parameters and computation cost of original models, our distilled VGG-based models obtain at least 6.5$\times$ speed-up on an Nvidia 1080 GPU and even achieve state-of-the-art performance. Our code and models are available at {\url{https://github.com/HCPLab-SYSU/SKT}}.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes