Compact Deep Aggregation for Set Retrieval

by   Yujie Zhong, et al.

The objective of this work is to learn a compact embedding of a set of descriptors that is suitable for efficient retrieval and ranking, whilst maintaining discriminability of the individual descriptors. We focus on a specific example of this general problem – that of retrieving images containing multiple faces from a large scale dataset of images. Here the set consists of the face descriptors in each image, and given a query for multiple identities, the goal is then to retrieve, in order, images which contain all the identities, all but one, To this end, we make the following contributions: first, we propose a CNN architecture – SetNet– to achieve the objective: it learns face descriptors and their aggregation over a set to produce a compact fixed length descriptor designed for set retrieval, and the score of an image is a count of the number of identities that match the query; second, we show that this compact descriptor has minimal loss of discriminability up to two faces per image, and degrades slowly after that – far exceeding a number of baselines; third, we explore the speed vs. retrieval quality trade-off for set retrieval using this compact descriptor; and, finally, we collect and annotate a large dataset of images containing various number of celebrities, which we use for evaluation and is publicly released.


page 2

page 5

page 8

page 16

page 17

page 18


GhostVLAD for set-based face recognition

The objective of this paper is to learn a compact representation of imag...

Writer Identification and Writer Retrieval Based on NetVLAD with Re-ranking

This paper addresses writer identification and retrieval which is a chal...

Voronoi-based compact image descriptors: Efficient Region-of-Interest retrieval with VLAD and deep-learning-based descriptors

We investigate the problem of image retrieval based on visual queries wh...

Interferences in match kernels

We consider the design of an image representation that embeds and aggreg...

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

Query expansion is a popular method to improve the quality of image retr...

Towards Automated Biometric Identification of Sea Turtles (Chelonia mydas)

Passive biometric identification enables wildlife monitoring with minima...

Texture Retrieval in the Wild through detection-based attributes

Capturing the essence of a textile image in a robust way is important to...

Please sign up or login with your details

Forgot password? Click here to reset