Related papers: A Convolutional Vision Transformer for Semantic Se…
We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an…
The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range…
This paper presents a method for estimating significant wave height (Hs) from sparse S_pectral P_oint using a T_ransformer-based approach (SPT). Based on empirical observations that only a minority of spectral points with strong power…
Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…
A central objective in computer vision is to design models with appropriate 2-D inductive bias. Desiderata for 2D inductive bias include two-dimensional position awareness, dynamic spatial locality, and translation and permutation…
Under the sea, visible spectrum cameras have limited sensing capacity, being able to detect objects only in clear water, but in a constrained range. Considering any sea water condition, sonars are more suitable to support autonomous…
Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with artificial or low-frequency noise. In this work, we propose…
The primary aim of Audio-Visual Segmentation (AVS) is to precisely identify and locate auditory elements within visual scenes by accurately predicting segmentation masks at the pixel level. Achieving this involves comprehensively…
Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…
Due to the scarcity and specific imaging characteristics in medical images, light-weighting Vision Transformers (ViTs) for efficient medical image segmentation is a significant challenge, and current studies have not yet paid attention to…
The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…
We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth learns…
This paper proposes a novel transformer-based model architecture for medical imaging problems involving analysis of vertebrae. It considers two applications of such models in MR images: (a) detection of spinal metastases and the related…
Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper,…
Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and…
Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low signal-to-noise…
The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features…
Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels, which are crucial…
The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information.…
Accurately segmenting roads is challenging due to substantial intra-class variations, indistinct inter-class distinctions, and occlusions caused by shadows, trees, and buildings. To address these challenges, attention to important texture…