Related papers: CARL: Camera-Agnostic Representation Learning for …

We study the problem of passive imaging through convolutive channels. A scene is illuminated with an unknown, unstructured source, and the measured response is the convolution of this source with multiple channel responses, each of which is…

Synthetic Aperture Radar (SAR) images are often contaminated by a multiplicative noise known as speckle. Speckle makes the processing and interpretation of SAR images difficult. We propose a deep learning-based approach called, Image…

Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning…

Blind deconvolution aims to recover an original image from a blurred version in the case where the blurring kernel is unknown. It has wide applications in diverse fields such as astronomy, microscopy, and medical imaging. Blind…

Deformable multi-contrast image registration is a challenging yet crucial task due to the complex, non-linear intensity relationships across different imaging contrasts. Conventional registration methods typically rely on iterative…

The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended…

Agents capable of accomplishing complex tasks through multiple interactions with the environment have emerged as a popular research direction. However, in such multi-step settings, the conventional group-level policy optimization algorithm…

Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be learned efficiently using self-supervision, and they can…

Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…

Long-tailed image classification remains a long-standing challenge, as real-world data typically follow highly imbalanced distributions where a few head classes dominate and many tail classes contain only limited samples. This imbalance…

Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel…

Detecting AI-generated images remains a significant challenge because detectors trained on specific generators often fail to generalize to unseen models; however, while pixel-level artifacts vary across models, frequency-domain signatures…

A plethora of machine learning methods have been applied to imaging data, enabling the construction of clinically relevant imaging signatures of neurological and neuropsychiatric diseases. Oftentimes, such methods don't explicitly model the…

Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in…

Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural…

We propose X-NeRF, a novel method to learn a Cross-Spectral scene representation given images captured from cameras with different light spectrum sensitivity, based on the Neural Radiance Fields formulation. X-NeRF optimizes camera poses…

Tactile representation learning (TRL) equips robots with the ability to leverage touch information, boosting performance in tasks such as environment perception and object manipulation. However, the heterogeneity of tactile sensors results…

Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement. Existing methods for reconstructing Hyperspectral Image (HSI) typically involve learning mappings from a 2D…

The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images. Many pretext tasks lead…

Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical adaptation"…