Related papers: SARA: Scene-Aware Reconstruction Accelerator
Among various sensors for assisted and autonomous driving systems, automotive radar has been considered as a robust and low-cost solution even in adverse weather or lighting conditions. With the recent development of radar technologies and…
We present AI-SARAH, a practical variant of SARAH. As a variant of SARAH, this algorithm employs the stochastic recursive gradient yet adjusts step-size based on local geometry. AI-SARAH implicitly computes step-size and efficiently…
Low-Rank Adaptation (LoRA) has emerged as a dominant method in Parameter-Efficient Fine-Tuning (PEFT) for large language models, which augments the transformer layer with one down-projection $A$ and one up-projection $B$. However, LoRA's…
Localizing objects and parts from natural language in 3D space is essential for robotics, AR, and embodied AI, yet existing methods face a trade-off between the accuracy and geometric consistency of per-scene optimization and the efficiency…
Deep learning architectures have achieved state-of-the-art (SOTA) performance on computer vision tasks such as object detection and image segmentation. This may be attributed to the use of over-parameterized, monolithic deep learning…
Incremental few-shot semantic segmentation (IFSS) aims to incrementally extend a semantic segmentation model to novel classes according to only a few pixel-level annotated data, while preserving its segmentation capability on previously…
X-ray images ease the diagnosis and treatment process due to their rapid imaging speed and high resolution. However, due to the projection process of X-ray imaging, much spatial information has been lost. To accurately provide efficient…
Deep learning has driven significant progress in object detection using Synthetic Aperture Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle to effectively integrate local and global information,…
Surface reconstruction from magnetic resonance (MR) imaging data is indispensable in medical image analysis and clinical research. A reliable and effective reconstruction tool should: be fast in prediction of accurate well localised and…
Remote Sensing Image-Text Retrieval (RSITR) is pivotal for knowledge services and data mining in the remote sensing (RS) domain. Considering the multi-scale representations in image content and text vocabulary can enable the models to learn…
Text-based person search aims to retrieve the specified person images given a textual description. The key to tackling such a challenging task is to learn powerful multi-modal representations. Towards this, we propose a Relation and…
Composed image retrieval (CIR) is a vision language task that retrieves a target image using a reference image and modification text, enabling intuitive specification of desired changes. While effectively fusing visual and textual…
Single Image Super-Resolution (SISR) is a crucial task in low-level computer vision, aiming to reconstruct high-resolution images from low-resolution counterparts. Conventional attention mechanisms have significantly improved SISR…
Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when…
Single image super-resolution is a well-known downstream task which aims to restore low-resolution images into high-resolution images. At present, models based on Transformers have shone brightly in the field of super-resolution due to…
Generative models have demonstrated significant success in anomaly detection and segmentation over the past decade. Recently, diffusion models have emerged as a powerful alternative, outperforming previous approaches such as GANs and VAEs.…
Object detection in satellite-borne Synthetic Aperture Radar (SAR) imagery holds immense potential in tasks such as urban monitoring and disaster response. However, the inherent complexities of SAR data and the scarcity of annotations…
Most object-level mapping systems in use today make use of an upstream learned object instance segmentation model. If we want to teach them about a new object or segmentation class, we need to build a large dataset and retrain the system.…
Near-field localization for ISAC requires large-aperture arrays, making fully-digital implementations prohibitively complex and costly. While sparse subarray architectures can reduce cost, they introduce severe estimation ambiguity from…
The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits of human-in-the-loop collection paradigms. To break this…