ACTNET: end-to-end learning of feature activations and multi-stream aggregation for effective instance image retrieval

07/12/2019
by   Syed Sameed Husain, et al.
4

We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable activation layer designed to improve the signal-to-noise ratio (SNR) of deep convolutional feature maps. Further, we introduce a controlled multi-stream aggregation, where complementary deep features from different convolutional layers are optimally transformed and balanced using our novel activation layers, before aggregation into a global descriptor. Importantly, the learnable parameters of our activation blocks are explicitly trained, together with the CNN parameters, in an end-to-end manner minimising triplet loss. This means that our network jointly learns the CNN filters and their optimal activation and aggregation for retrieval tasks. To our knowledge, this is the first time parametric functions have been used to control and learn optimal aggregation. We conduct an in-depth experimental study on three non-linear activation functions: Sine-Hyperbolic, Exponential and modified Weibull, showing that while all bring significant gains the Weibull function performs best thanks to its ability to equalise strong activations. The results clearly demonstrate that our ACTNET architecture significantly enhances the discriminative power of deep features, improving significantly over the state-of-the-art retrieval results on all datasets.

READ FULL TEXT

page 3

page 5

page 7

page 11

page 14

research
07/12/2019

ACTNET: end-to-end learning of feature activations and aggregation for effective instance image retrieval

We propose a novel CNN architecture called ACTNET for robust instance im...
research
06/15/2019

REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval

This paper addresses the problem of very large-scale image retrieval, fo...
research
09/20/2019

Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval

One of the key challenges of deep learning based image retrieval remains...
research
12/04/2020

DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation

In this work, we introduce a Denser Feature Network (DenserNet) for visu...
research
03/03/2019

MILDNet: A Lightweight Single Scaled Deep Ranking Architecture

Multi-scale deep CNN architecture [1, 2, 3] successfully captures both f...
research
04/03/2018

Unsupervised Semantic-based Aggregation of Deep Convolutional Features

In this paper, we propose a simple but effective semantic-based aggregat...
research
08/09/2016

OnionNet: Sharing Features in Cascaded Deep Classifiers

The focus of our work is speeding up evaluation of deep neural networks ...

Please sign up or login with your details

Forgot password? Click here to reset