Related papers: Reciprocal Space Attention for Learning Long-Range…

In recent years, human pose estimation has made significant progress through the implementation of deep learning techniques. However, these techniques still face limitations when confronted with challenging scenarios, including occlusion,…

Self-attention (SA), which encodes vector sequences according to their pairwise similarity, is widely used in speech recognition due to its strong context modeling ability. However, when applied to long sequence data, its accuracy is…

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…

While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such…

Human-centered environments are rich with a wide variety of spatial relations between everyday objects. For autonomous robots to operate effectively in such environments, they should be able to reason about these relations and generalize…

Correlations between input parameters play a crucial role in many scientific classification tasks, since these are often related to fundamental laws of nature. For example, in high energy physics, one of the common deep learning use-cases…

A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. However, RNNs are fundamentally unable to randomly access…

Recent attention-based image inpainting methods have made inspiring progress by modeling long-range dependencies within a single image. However, they tend to generate blurry contents since the correlation between each pixel pairs is always…

Transformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct…

We introduce the modified planar rotator method (MPRS), a physically inspired machine learning method for spatial/temporal regression. MPRS is a non-parametric model which incorporates spatial or temporal correlations via short-range,…

A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones. Among them, some restore the missing details of each frame via exploring the spatiotemporal information of…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

The random phase approximation (RPA) has emerged as a prominent first-principles method in material science, particularly to study the adsorption and chemisorption of small molecules on surfaces. However, its widespread application is…

Whole Slide Images (WSIs) are high-resolution digital scans widely used in medical diagnostics. WSI classification is typically approached using Multiple Instance Learning (MIL), where the slide is partitioned into tiles treated as…

Reliable segmentation of retinal vessels can be employed as a way of monitoring and diagnosing certain diseases, such as diabetes and hypertension, as they affect the retinal vascular structure. In this work, we propose the Residual Spatial…

The inclusion of long-range electrostatics in atomistic machine learning (ML) is receiving increasing attention for achieving quantum-mechanical accuracy in predicting a wide range of molecular and material properties. However, there is…

Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries. Traditional Referring Image…

We present lambda layers -- an alternative framework to self-attention -- for capturing long-range interactions between an input and structured contextual information (e.g. a pixel surrounded by other pixels). Lambda layers capture such…

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

Single image super-resolution (SR) has long posed a challenge in the field of computer vision. While the advent of deep learning has led to the emergence of numerous methods aimed at tackling this persistent issue, the current methodologies…