Log In Sign Up

DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval

by   Giorgos Kordopatis-Zilos, et al.

In this paper, we address the problem of high performance and computationally efficient content-based video retrieval in large-scale datasets. Current methods typically propose either: (i) fine-grained approaches employing spatio-temporal representations and similarity calculations, achieving high performance at a high computational cost or (ii) coarse-grained approaches representing/indexing videos as global vectors, where the spatio-temporal structure is lost, providing low performance but also having low computational cost. In this work, we propose a Knowledge Distillation framework, which we call Distill-and-Select (DnS), that starting from a well-performing fine-grained Teacher Network learns: a) Student Networks at different retrieval performance and computational efficiency trade-offs and b) a Selection Network that at test time rapidly directs samples to the appropriate student to maintain both high retrieval performance and high computational efficiency. We train several students with different architectures and arrive at different trade-offs of performance and efficiency, i.e., speed and storage requirements, including fine-grained students that store index videos using binary representations. Importantly, the proposed scheme allows Knowledge Distillation in large, unlabelled datasets – this leads to good students. We evaluate DnS on five public datasets on three different video retrieval tasks and demonstrate a) that our students achieve state-of-the-art performance in several cases and b) that our DnS framework provides an excellent trade-off between retrieval performance, computational speed, and storage space. In specific configurations, our method achieves similar mAP with the teacher but is 20 times faster and requires 240 times less storage space. Our collected dataset and implementation are publicly available:


page 2

page 10

page 11


Context Unaware Knowledge Distillation for Image Retrieval

Existing data-dependent hashing methods use large backbone networks with...

It's All in the Head: Representation Knowledge Distillation through Classifier Sharing

Representation knowledge distillation aims at transferring rich informat...

Self-Referenced Deep Learning

Knowledge distillation is an effective approach to transferring knowledg...

Fine-Grained Distillation for Long Document Retrieval

Long document retrieval aims to fetch query-relevant documents from a la...

ViSiL: Fine-grained Spatio-Temporal Video Similarity Learning

In this paper we introduce ViSiL, a Video Similarity Learning architectu...

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

End-to-end text spotting has attached great attention recently due to it...

Collaborative Group Learning

Collaborative learning has successfully applied knowledge transfer to gu...