Timezone: »
While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled information to local features. The operators are cheap, both in terms of number of added parameters and computational complexity, and can be integrated directly in existing architectures to improve their performance. Experiments on several datasets show that gather-excite can bring benefits comparable to increasing the depth of a CNN at a fraction of the cost. For example, we find ResNet-50 with gather-excite operators is able to outperform its 101-layer counterpart on ImageNet with no additional learnable parameters. We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.
Author Information
Jie Hu (Momenta)
Li Shen (University of Oxford)
Samuel Albanie (Oxford University)
Gang Sun (Momenta)
Andrea Vedaldi (Facebook AI Research and University of Oxford)
More from the Same Authors
-
2022 Poster: RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection »
Hangjie Yuan · Jianwen Jiang · Samuel Albanie · Tao Feng · Ziyuan Huang · Dong Ni · Mingqian Tang -
2022 : Direct LiDAR-based object detector training from automated 2D detections »
Robert McCraith · Eldar Insafutdinov · Lukas Neumann · Andrea Vedaldi -
2023 Poster: Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion »
Yash Bhalgat · Iro Laina · João Henriques · Andrea Vedaldi · Andrew Zisserman -
2023 Poster: Improving Category Discovery When No Representation Rules Them All »
Sagar Vaze · Andrea Vedaldi · Andrew Zisserman -
2023 Poster: EPIC Fields: Marrying 3D Geometry and Video Understanding »
Vadim Tschernezki · Ahmad Darkhalil · Zhifan Zhu · David Fouhey · Iro Laina · Diane Larlus · Dima Damen · Andrea Vedaldi -
2022 Spotlight: RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection »
Hangjie Yuan · Jianwen Jiang · Samuel Albanie · Tao Feng · Ziyuan Huang · Dong Ni · Mingqian Tang -
2022 Poster: ReCo: Retrieve and Co-segment for Zero-shot Transfer »
Gyungin Shin · Weidi Xie · Samuel Albanie -
2022 Poster: Unsupervised Multi-Object Segmentation by Predicting Probable Motion Patterns »
Laurynas Karazija · Subhabrata Choudhury · Iro Laina · Christian Rupprecht · Andrea Vedaldi -
2021 Workshop: The pre-registration workshop: an alternative publication model for machine learning research »
Samuel Albanie · João Henriques · Luca Bertinetto · Alex Hernandez-Garcia · Hazel Doughty · Gul Varol -
2020 Workshop: The pre-registration experiment: an alternative publication model for machine learning research »
Luca Bertinetto · João Henriques · Samuel Albanie · Michela Paganini · Gul Varol -
2020 Poster: Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning »
Iro Laina · Ruth Fong · Andrea Vedaldi -
2020 Poster: RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces »
Sebastien Ehrhardt · Oliver Groth · Aron Monszpart · Martin Engelcke · Ingmar Posner · Niloy Mitra · Andrea Vedaldi -
2019 Poster: Fixing the train-test resolution discrepancy »
Hugo Touvron · Andrea Vedaldi · Matthijs Douze · Herve Jegou -
2018 Poster: Modelling and unsupervised learning of symmetric deformable object categories »
James Thewlis · Hakan Bilen · Andrea Vedaldi -
2018 Poster: Unsupervised Learning of Object Landmarks through Conditional Image Generation »
Tomas Jakab · Ankush Gupta · Hakan Bilen · Andrea Vedaldi -
2017 Workshop: Interpreting, Explaining and Visualizing Deep Learning - Now what ? »
Klaus-Robert Müller · Andrea Vedaldi · Lars K Hansen · Wojciech Samek · Grégoire Montavon -
2017 Poster: Learning multiple visual domains with residual adapters »
Sylvestre-Alvise Rebuffi · Hakan Bilen · Andrea Vedaldi -
2017 Spotlight: Learning multiple visual domains with residual adapters »
Sylvestre-Alvise Rebuffi · Hakan Bilen · Andrea Vedaldi -
2017 Poster: Unsupervised learning of object frames by dense equivariant image labelling »
James Thewlis · Hakan Bilen · Andrea Vedaldi -
2017 Oral: Unsupervised learning of object frames by dense equivariant image labelling »
James Thewlis · Hakan Bilen · Andrea Vedaldi -
2016 Poster: Learning feed-forward one-shot learners »
Luca Bertinetto · João Henriques · Jack Valmadre · Philip Torr · Andrea Vedaldi -
2016 Poster: Integrated perception with recurrent multi-task neural networks »
Hakan Bilen · Andrea Vedaldi -
2013 Poster: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2013 Spotlight: Deep Fisher Networks for Large-Scale Image Classification »
Karen Simonyan · Andrea Vedaldi · Andrew Zisserman -
2011 Poster: Pylon Model for Semantic Segmentation »
Victor Lempitsky · Andrea Vedaldi · Andrew Zisserman -
2010 Poster: Simultaneous Object Detection and Ranking with Weak Supervision »
Matthew B Blaschko · Andrea Vedaldi · Andrew Zisserman -
2009 Poster: Structured output regression for detection with partial truncation »
Andrea Vedaldi · Andrew Zisserman -
2006 Poster: A Rate-Distortion Approach to Joint Pattern Alignment »
Andrea Vedaldi