Related papers: PVEs: Position-Velocity Encoders for Unsupervised …
We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specific language. Our framework naturally incorporates symbolic…
Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend…
We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…
We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs…
The lack of annotated training data in bioacoustics hinders the use of large-scale neural network models trained in a supervised way. In order to leverage a large amount of unannotated audio data, we propose AVES (Animal Vocalization…
Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not…
Within the context of trajectory planning for autonomous vehicles this paper proposes methods for efficient encoding of motion primitives in neural networks on top of model-based and gradient-free reinforcement learning. It is distinguished…
With the increasing use of high-precision system analysis programs in nuclear engineering, the number of high-fidelity computational data for accident simulation is exploding. Therefore, an algorithm that can achieve both automatic…
Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…
We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen…
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…
Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…
Generic re-usable pre-trained image representation encoders have become a standard component of methods for many computer vision tasks. As visual representations for robots however, their utility has been limited, leading to a recent wave…
Simulations of large-scale dynamical systems require expensive computations. Low-dimensional parametrization of high-dimensional states such as Proper Orthogonal Decomposition (POD) can be a solution to lessen the burdens by providing a…
Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image…
Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…
Positional encoding is important for vision transformer (ViT) to capture the spatial structure of the input image. General effectiveness has been proven in ViT. In our work we propose to train ViT to recognize the positional label of…
Vision-Language Models (VLMs) have demonstrated strong performance across various multimodal tasks, where position encoding plays a vital role in modeling both the sequential structure of textual information and the spatial structure of…
A novel stability-enhanced Gaussian process variational autoencoder (SEGP-VAE) is proposed for indirectly training a low-dimensional linear time invariant (LTI) system, using high-dimensional video data. The mean and covariance function of…
Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models have some…