Improving Robot Localisation by Ignoring Visual Distraction
Not on the map. Why?
Abstract (arXiv)
Attention is an important component of modern deep learning. However, less emphasis has been put on its inverse: ignoring distraction. Our daily lives require us to explicitly avoid giving attention to salient visual features that confound the task we are trying to accomplish. This visual prioritisation allows us to concentrate on important tasks while ignoring visual distractors. In this work, we introduce Neural Blindness, which gives an agent the ability to completely ignore objects or classes that are deemed distractors. More explicitly, we aim to render a neural network completely incapable of representing specific chosen classes in its latent space. In a very real sense, this makes the network "blind" to certain classes, allowing and agent to focus on what is important for a given task, and demonstrates how this can be used to improve localisation.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 25 Jul 2021.
Builds on
23 of 30 references.
References · 23
- 2017Neural Discrete Representation Learningcited by 4,650
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
- 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
- 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
- 2018Generative Image Inpainting with Contextual Attentioncited by 578
- 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
- 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
- 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
- 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 133
11 more
- 2015Deep Convolutional Inverse Graphics Networkcited by 121
- 2019DIVA: Domain Invariant Variational Autoencoderscited by 114
- 2018Invariant Representations without Adversarial Trainingcited by 111
- 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
- 2019Foreground-aware Image Inpaintingcited by 90
- 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
- 2019Disentangling Factors of Variation Using Few Labelscited by 57
- 2019Disentangled Representation Learning for 3D Face Shapecited by 48
- 2017Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environmentscited by 22
- 2019Variational Auto-Decoder: A Method for Neural Generative Modeling from Incomplete Datacited by 10
- 2017JADE: Joint Autoencoders for Dis-Entanglementcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.