Motion Invariance in Visual Environments
The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams, just as happens in nature. In this paper, we claim that their processing naturally leads to formulate the motion invariance principle, which enables the construction of a new theory of visual learning based on convolutional features. The theory addresses a number of intriguing questions that arise in natural vision, and offers a well-posed computational scheme for the discovery of convolutional filters over the retina. They are driven by the Euler-Lagrange differential equations derived from the principle of least cognitive action, that parallels laws of mechanics. Unlike traditional convolutional networks, which need massive supervision, the proposed theory offers a truly new scenario in which feature learning takes place by unsupervised processing of video signals. An experimental report of the theory is presented where we show that features extracted under motion invariance yield an improvement that can be assessed by measuring information-based indexes.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Enhancing Feature Tracking Reliability for Visual Navigation using Real-Time Safety Filter
Vision sensors are extensively used for localizing a robot's pose, particularly in environments where global localization tools such as GPS or motion capture systems are unavailable. In many visual navigation systems, lo…
Pose EstimationSimultaneous Localization and MappingVisual NavigationLearning Visual Features Under Motion Invariance
Humans are continuously exposed to a stream of visual data with a natural temporal structure. However, most successful computer vision algorithms work at image level, completely discarding the precious information carrie…
Improving the Generalization of Visual Navigation Policies using Invariance Regularization
Training agents to operate in one environment often yields overfitted models that are unable to generalize to the changes in that environment. However, due to the numerous variations that can occur in the real-world, the…
Reinforcement LearningReinforcement Learning (RL)Visual NavigationDomain Generalization via Text-Anchored Information Bottleneck
Visual recognition models often fail when deployed in new environments. Domain Generalization (DG) addresses this by learning representations that remain invariant to environment-specific variations. Recent approaches in…
Domain GeneralizationBeyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videos
Imitation from videos often fails when expert demonstrations and learner environments exhibit domain shifts, such as discrepancies in lighting, color, or texture. While visual randomization partially addresses this probl…
Data Augmentation