Related papers: SIEFormer: Spectral-Interpretable and -Enhanced Tr…

The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this…

Scientific machine learning often involves representing complex solution fields that exhibit high-frequency features such as sharp transitions, fine-scale oscillations, and localized structures. While implicit neural representations (INRs)…

The emergence of large foundation models has propelled significant advances in various domains. The Segment Anything Model (SAM), a leading model for image segmentation, exemplifies these advances, outperforming traditional methods.…

Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from images captured at different places and times. Recently, object Re-ID has achieved great success with the advances of Vision Transformers (ViT). However,…

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…

Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy. However, precise detection remains a considerable challenge due to subtle…

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Accurate ECG interpretation is vital, yet complex cardiac data and "black-box" AI models limit clinical utility. Inspired by Transformer architectures' success in NLP for understanding sequential data, we frame ECG as the heart's unique…

Breast cancer detection through mammography interpretation remains difficult because of the minimal nature of abnormalities that experts need to identify alongside the variable interpretations between readers. The potential of CNNs for…

This paper proposes CAT-MoEformer, a context-aware transformer with scene-conditioned mixture-of-experts (MoE) feed-forward networks, for proactive mmWave beam prediction from compressed uplink pilot observations. The spatial encoder…

Adapting image-pretrained backbones to video typically relies on time-domain adapters tuned to a single temporal scale. Our experiments show that these modules pick up static image cues and very fast flicker changes, while overlooking…

Binary segmentation is used to distinguish objects of interest from background, and is an active area of convolutional encoder-decoder network research. The current decoders are designed for specific objects based on the common backbones as…

Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, pure transformers are not entirely suitable for vehicle re-identification…

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…

Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications. Unfortunately, though witnessing the development of deep learning in HSI denoising area, existing convolution-based methods face…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

Convolutional blocks have played a crucial role in advancing medical image segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.…

Hyperspectral image (HSI) classification (HSIC) requires effective modeling of complex spatial-spectral dependencies under limited labeled data and high dimensionality. While transformer-based models have shown strong capability in…

Many real-world networks are characterized by directionality; however, the absence of an appropriate Fourier basis hinders the effective implementation of graph signal processing techniques. Inspired by discrete signal processing, where…