Related papers: Progress and outlook on advanced fly scans based o…
Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios. Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense…
Audio super-resolution aims to enhance low-resolution signals by creating high-frequency content. In this work, we modify the architecture of AERO (a state-of-the-art system for this task) for music super-resolution. SPecifically, we…
Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often suffer from inefficiencies, as their computational complexity…
Accurate building segmentation and height estimation from single-view RGB satellite imagery are fundamental for urban analytics, yet remain ill-posed due to structural variability and the high computational cost of global context modeling.…
The next generation of wide-area sky surveys offer the power to place extremely precise constraints on cosmological parameters and to test the source of cosmic acceleration. These observational programs will employ multiple techniques based…
Foundation models refer to deep learning models pretrained on large unlabeled datasets through self-supervised algorithms. In the Earth science and remote sensing communities, there is growing interest in transforming the use of Earth…
Scanamorphos is one of the public softwares available to post-process scan observations performed with the Herschel photometer arrays. This post-processing mainly consists in subtracting the total low-frequency noise (both its thermal and…
State space models (SSMs) have emerged as an efficient alternative to transformer-based models, offering linear complexity that scales better than transformers. One of the latest advances in SSMs, Mamba, introduces a selective scan…
Accurate medical image segmentation remains challenging due to blurred lesion boundaries (LBA), loss of high-frequency details (LHD), and difficulty in modeling long-range anatomical structures (DC-LRSS). Vision Mamba employs…
VADMamba pioneered the introduction of Mamba to Video Anomaly Detection (VAD), achieving high accuracy and fast inference through hybrid proxy tasks. Nevertheless, its heavy reliance on optical flow as auxiliary input and inter-task fusion…
Point cloud enhancement is the process of generating a high-quality point cloud from an incomplete input. This is done by filling in the missing details from a reference like the ground truth via regression, for example. In addition to…
Due to the long-range modeling ability and linear complexity property, Mamba has attracted considerable attention in point cloud analysis. Despite some interesting progress, related work still suffers from imperfect point cloud…
Multiple object tracking (MOT) from unmanned aerial vehicle (UAV) platforms requires efficient motion modeling. This is because UAV-MOT faces both local object motion and global camera motion. Motion blur also increases the difficulty of…
Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…
High throughput and low latency data processing is essential for systems requiring live decision making, control, and machine learning-optimized data reduction. We focus on two distinct use cases for in-flight streaming data processing for…
Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointly model local-global dynamics and handle nonstationarities…
Diffusion models currently demonstrate impressive performance over various generative tasks. Recent work on image diffusion highlights the strong capabilities of Mamba (state space models) due to its efficient handling of long-range…
State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent…
Mamba-based models, VMamba and Vim, are a recent family of vision encoders that offer promising performance improvements in many computer vision tasks. This paper compares Mamba-based models with traditional Convolutional Neural Networks…
Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the…