Learning with Average Precision: Training Image Retrieval with a Listwise Loss

06/18/2019
by   Jerome Revaud, et al.
0

Image retrieval can be formulated as a ranking problem where the goal is to order database images by decreasing similarity to the query. Recent deep models for image retrieval have outperformed traditional methods by leveraging ranking-tailored loss functions, but important theoretical and practical problems remain. First, rather than directly optimizing the global ranking, they minimize an upper-bound on the essential loss, which does not necessarily result in an optimal mean average precision (mAP). Second, these methods require significant engineering efforts to work well, e.g. special pre-training and hard-negative mining. In this paper we propose instead to directly optimize the global mAP by leveraging recent advances in listwise loss formulations. Using a histogram binning approximation, the AP can be differentiated and thus employed to end-to-end learning. Compared to existing losses, the proposed method considers thousands of images simultaneously at each iteration and eliminates the need for ad hoc tricks. It also establishes a new state of the art on many standard retrieval benchmarks. Models and evaluation scripts have been made available at https://europe.naverlabs.com/Deep-Image-Retrieval/

READ FULL TEXT
research
10/01/2021

Robust and Decomposable Average Precision for Image Retrieval

In image retrieval, standard evaluation metrics rely on score ranking, e...
research
09/15/2023

Optimization of Rank Losses for Image Retrieval

In image retrieval, standard evaluation metrics rely on score ranking, a...
research
07/05/2022

Hierarchical Average Precision Training for Pertinent Image Retrieval

Image Retrieval is commonly evaluated with Average Precision (AP) or Rec...
research
09/06/2020

Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval

Optimising a ranking-based metric, such as Average Precision (AP), is no...
research
02/09/2021

Rethinking Ranking-based Loss Functions: Only Penalizing Negative Instances before Positive Ones is Enough

Optimising the approximation of Average Precision (AP) has been widely s...
research
01/31/2022

Learning Super-Features for Image Retrieval

Methods that combine local and global features have recently shown excel...
research
10/03/2018

A deep learning pipeline for product recognition on store shelves

Recognition of grocery products in store shelves poses peculiar challeng...

Please sign up or login with your details

Forgot password? Click here to reset