Related papers: Structured Domain Randomization: Bridging the Real…

Both Dimensionality Reduction (DR) and Graph Drawing (GD) aim to visualize abstract, non-linear structures, yet rely on different optimization paradigms. This contrast is evident in Multidimensional Scaling (MDS), which typically depends on…

A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts…

Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute…

In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realistic results, most of them have difficulty handling…

A practical approach to learning robot skills, often termed sim2real, is to train control policies in simulation and then deploy them on a real robot. Popular techniques to improve the sim2real transfer build on domain randomization (DR) --…

Single-source domain generalization (SDG) for object detection is a challenging yet essential task as the distribution bias of the unseen domain degrades the algorithm performance significantly. However, existing methods attempt to extract…

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Background: Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate…

Object detection is one of the key target tasks of interest in the context of civil and military applications. In particular, the real-world deployment of target detection methods is pivotal in the decision-making process during military…

We introduce a generic visual descriptor, termed as distribution aware retinal transform (DART), that encodes the structural context using log-polar grids for event cameras. The DART descriptor is applied to four different problems, namely…

Deep learning in computer vision has achieved great success with the price of large-scale labeled training data. However, exhaustive data annotation is impracticable for each task of all domains of interest, due to high labor costs and…

Soft robots are gaining popularity thanks to their intrinsic safety to contacts and adaptability. However, the potentially infinite number of Degrees of Freedom makes their modeling a daunting task, and in many cases only an approximated…

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information.…

Dimensionality Reduction (DR) methods are widely used to visualize high-dimensional data. One key task in DR-based analysis is discovering neighborhoods, which relies on analyzing the fine-grained local structure of a projection. However,…

Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the…

Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving two stages of sampling: Firstly, we regress from…

Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are…

Spatial Description Resolution, as a language-guided localization task, is proposed for target location in a panoramic street view, given corresponding language descriptions. Explicitly characterizing an object-level relationship while…

Most of the real world scenes have a very high dynamic range (HDR). The mobile phone cameras and the digital cameras available in markets are limited in their capability in both the range and spatial resolution. Same argument can be posed…

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most…