Related papers: SARA: Scene-Aware Reconstruction Accelerator
We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in…
This manuscript introduces SARFormer, a modified Vision Transformer (ViT) architecture designed for processing one or multiple synthetic aperture radar (SAR) images. Given the complex image geometry of SAR data, we propose an acquisition…
This work presents TREA, a low-precision time-multiplexed and resource-efficient edge-AI accelerator for object detection and classification, targeting stringent area-power-latency constraints of edge vision platforms. The proposed…
Scene flow estimation, which predicts the 3D motion of scene points from point clouds, is a core task in autonomous driving and many other 3D vision applications. Existing methods either suffer from structure distortion due to ignorance of…
Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes. While entity-level knowledge graphs support structured access, they are costly to construct and maintain,…
Sharpness-aware minimization (SAM) seeks the minima with a flat loss landscape to improve the generalization performance in machine learning tasks, including fine-tuning. However, its extra parameter perturbation step doubles the…
Synthetic Aperture Radar (SAR) images have proven to be a valuable cue for multimodal Land Cover Classification (LCC) when combined with RGB images. Most existing studies on cross-modal fusion assume that consistent feature information is…
Retrieving 3D objects in complex indoor environments using only a masked 2D image and a natural language description presents significant challenges. The ROOMELSA challenge limits access to full 3D scene context, complicating reasoning…
Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural…
The Back-Projection Algorithm (BPA) is a time domain matched filtering technique to form synthetic aperture radar (SAR) images. To produce high quality BPA images, precise navigation data for the radar platform must be known. Any error in…
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…
Charged particle accelerators play a pivotal role in scientific research, industry, and medical applications. Among them, radiofrequency (RF) accelerators offer a promising approach for achieving high-energy particle acceleration in compact…
Synthetic aperture radar (SAR) imaging plays a critical role in all-weather, day-and-night remote sensing, yet reconstruction is often challenged by noise, undersampling, and complex scattering scenarios. Conventional methods, including…
Current deep learning-based object detection for Synthetic Aperture Radar (SAR) imagery mainly adopts optical image methods, treating targets as texture patches while ignoring inherent electromagnetic scattering mechanisms. Though…
The structural re-parameterization (SRP) technique is a novel deep learning technique that achieves interconversion between different network architectures through equivalent parameter transformations. This technique enables the mitigation…
Sequential recommendation (SR) aims to predict a user's next action by learning from their historical interaction sequences. In real-world applications, these models require periodic updates to adapt to new interactions and evolving user…
Address event representation (AER) cameras have recently attracted more attention due to the advantages of high temporal resolution and low power consumption, compared with traditional frame-based cameras. Since AER cameras record the…
Modern large-scale recommender systems employ multi-stage ranking funnel (Retrieval, Pre-ranking, Ranking) to balance engagement and computational constraints (latency, CPU). However, the initial retrieval stage, often relying on efficient…
Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus on descriptor fine-tuning or fixed sampling strategies yet neglect the…
We introduce R-Sparse R-CNN, a novel pipeline for oriented ship detection in Synthetic Aperture Radar (SAR) images that leverages sparse learnable proposals enriched with background contextual information, termed background-aware proposals…