Learning to Localize in New Environments from Synthetic Training Data
- URL: http://arxiv.org/abs/2011.04539v2
- Date: Mon, 21 Jun 2021 08:34:34 GMT
- Title: Learning to Localize in New Environments from Synthetic Training Data
- Authors: Dominik Winkelbauer, Maximilian Denninger, Rudolph Triebel
- Abstract summary: We present an approach that can generalize to new scenes by applying specific changes to the model architecture.
Our approach outperforms the 5-point algorithm using SIFT features on equally big images.
- Score: 26.194505911908585
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Most existing approaches for visual localization either need a detailed 3D
model of the environment or, in the case of learning-based methods, must be
retrained for each new scene. This can either be very expensive or simply
impossible for large, unknown environments, for example in search-and-rescue
scenarios. Although there are learning-based approaches that operate
scene-agnostically, the generalization capability of these methods is still
outperformed by classical approaches. In this paper, we present an approach
that can generalize to new scenes by applying specific changes to the model
architecture, including an extended regression part, the use of hierarchical
correlation layers, and the exploitation of scale and uncertainty information.
Our approach outperforms the 5-point algorithm using SIFT features on equally
big images and additionally surpasses all previous learning-based approaches
that were trained on different data. It is also superior to most of the
approaches that were specifically trained on the respective scenes. We also
evaluate our approach in a scenario where only very few reference images are
available, showing that under such more realistic conditions our learning-based
approach considerably exceeds both existing learning-based and classical
methods.
Related papers
- Generalization Properties of Retrieval-based Models [50.35325326050263]
Retrieval-based machine learning methods have enjoyed success on a wide range of problems.
Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored.
We present a formal treatment of retrieval-based models to characterize their generalization ability.
arXiv Detail & Related papers (2022-10-06T00:33:01Z) - Making Look-Ahead Active Learning Strategies Feasible with Neural
Tangent Kernels [6.372625755672473]
We propose a new method for approximating active learning acquisition strategies that are based on retraining with hypothetically-labeled candidate data points.
Although this is usually infeasible with deep networks, we use the neural tangent kernel to approximate the result of retraining.
arXiv Detail & Related papers (2022-06-25T06:13:27Z) - Model-Based Deep Learning: On the Intersection of Deep Learning and
Optimization [101.32332941117271]
Decision making algorithms are used in a multitude of different applications.
Deep learning approaches that use highly parametric architectures tuned from data without relying on mathematical models are becoming increasingly popular.
Model-based optimization and data-centric deep learning are often considered to be distinct disciplines.
arXiv Detail & Related papers (2022-05-05T13:40:08Z) - EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art
Few-Shot Classification with Simple Ingredients [2.0935101589828244]
Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems.
We propose a simple methodology, that reaches or even beats state of the art performance on multiple standardized benchmarks of the field.
arXiv Detail & Related papers (2022-01-24T14:08:23Z) - Why-So-Deep: Towards Boosting Previously Trained Models for Visual Place
Recognition [12.807343105549409]
We present an intelligent method, MAQBOOL, to amplify the power of pre-trained models for better image recall.
We achieve comparable image retrieval results at a low descriptor dimension (512-D), compared to the high descriptor dimension (4096-D) of state-of-the-art methods.
arXiv Detail & Related papers (2022-01-10T08:39:06Z) - Model-Based Deep Learning [155.063817656602]
Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques.
Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance.
We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
arXiv Detail & Related papers (2020-12-15T16:29:49Z) - Learning to Generalize Unseen Domains via Memory-based Multi-Source
Meta-Learning for Person Re-Identification [59.326456778057384]
We propose the Memory-based Multi-Source Meta-Learning framework to train a generalizable model for unseen domains.
We also present a meta batch normalization layer (MetaBN) to diversify meta-test features.
Experiments demonstrate that our M$3$L can effectively enhance the generalization ability of the model for unseen domains.
arXiv Detail & Related papers (2020-12-01T11:38:16Z) - Region Comparison Network for Interpretable Few-shot Image
Classification [97.97902360117368]
Few-shot image classification has been proposed to effectively use only a limited number of labeled examples to train models for new classes.
We propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works.
We also present a new way to generalize the interpretability from the level of tasks to categories.
arXiv Detail & Related papers (2020-09-08T07:29:05Z) - Move-to-Data: A new Continual Learning approach with Deep CNNs,
Application for image-class recognition [0.0]
It is necessary to pre-train the model at a "training recording phase" and then adjust it to the new coming data.
We propose a fast continual learning layer at the end of the neuronal network.
arXiv Detail & Related papers (2020-06-12T13:04:58Z) - Guided Uncertainty-Aware Policy Optimization: Combining Learning and
Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state.
reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle.
In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
arXiv Detail & Related papers (2020-05-21T19:47:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.