Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval.
Andrew Brown,Weidi Xie,Vicky Kalogeiton,Andrew Zisserman +3 more
- pp 677-694
Reads0
Chats0
TLDR
Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation and improves the performance over the state-of-the-art, especially for larger-scale datasets, thus demonstrating the effectiveness and scalability of Smooth-AP to real-world scenarios.Abstract:
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods. To this end, we introduce an objective that optimises instead a smoothed approximation of AP, coined Smooth-AP. Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation. We also present an analysis for why directly optimising the ranking based metric of AP offers benefits over other deep metric learning losses.read more
Citations
More filters
Journal ArticleDOI
HashFormer: Vision Transformer Based Deep Hashing for Image Retrieval
TL;DR: This work proposes a pure transformer-based framework, called as HashFormer, to tackle the deep hashing task, and utilizes vision transformer (ViT) as its backbone, and treats binary codes as the intermediate representations for the authors' surrogate task, i.e., image classification.
Posted Content
Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval
TL;DR: A variational approximation of the posterior, called the Bayesian triplet loss, is derived that produces state-of-the-art uncertainty estimates and matches the predictive performance of current state of theart methods.
Proceedings ArticleDOI
Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
TL;DR: A simple and effective learning- based method for computing a discriminative 3D point cloud descriptor for place recognition purposes, based on a sparse voxelized representation, enhanced with channel attention blocks.
Posted Content
Deep image retrieval: a survey
Wei Chen,Yu Liu,Weiping Wang,Erwin M. Bakker,Theodoros Georgiou,Paul Fieguth,Li Liu,Michael S. Lew +7 more
TL;DR: In this article, the authors organize and review recent content-based image retrieval (CBIR) works that are developed based on deep learning algorithms and techniques, including insights and techniques from recent papers.
Journal ArticleDOI
Rank-in-Rank Loss for Person Re-identification
TL;DR: The proposed Differentiable Retrieval-Sort Loss (DRSL) can improve the performance of the state-of-the-art re-ID models, thus demonstrating its effectiveness and superiority on the re- ID task.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal ArticleDOI
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
Journal ArticleDOI
Squeeze-and-Excitation Networks
TL;DR: This work proposes a novel architectural unit, which is term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and finds that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost.
Book
Introduction to Information Retrieval
TL;DR: In this article, the authors present an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections.