Adam Prügel-Bennett — accepted AI-conference papers

2021

Leveraging Metadata in Representation Learning With Georeferenced Seafloor Imagery

Takaki Yamada, Miquel Massot-Campos, Adam Prügel-Bennett, Stefan B. Williams, Oscar Pizarro, Blair Thornton

RA-L 2021

Camera equipped Autonomous Underwater Vehicles (AUVs) are now routinely used in seafloor surveys. Obtaining effective representations from the images they collect can enable perception-aware robotic exploration such as information-gain-guided path planning and target-driven visual navigation. This l

Cited by 12 Source ↗Scholar ↗

2020

FSPool: Learning Set Representations with Featurewise Sort Pooling

Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

ICLR 2020poster

Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This can be used to construct a permutation-equivariant auto-encoder…

Cited by 94 Source ↗code ↗Scholar ↗

2019

Learning Representations of Sets through Optimized Permutations

Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

ICLR 2019poster

Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be further processed to learn a permutation-invariant representatio…

Cited by 32 Source ↗PDF ↗Scholar ↗

2019

Saliency Map on Cnns for Protein Secondary Structure Prediction

Guillermo Romero Moreno, Mahesan Niranjan, Adam Prügel-Bennett

ICASSP 2019accepted

Deep learning, a powerful methodology for data-driven modelling, has been shown to be useful in tackling several problems in the biomedical domain. However, deep neural architectures lack interpretability of how predictions from them are made on any test input. While several approaches to "opening t…

Cited by 0 Source ↗Scholar ↗

2018

Learning to Count Objects in Natural Images for Visual Question Answering

Yan Zhang, Jonathon Hare, Adam Prügel-Bennett

ICLR 2018poster

Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposal…

Cited by 260 Source ↗PDF ↗code ↗Scholar ↗