Related papers: Local Attention Transformers for High-Detail Optic…

In order to decrease the steady-state error and reduce the computational complexity and increase the ability to identify a large unknown system, a convex combination of overlap-save frequency-domain adaptive filters (COSFDAF) algorithm is…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts. However, existing self-attention methods either adopt sparse global attention…

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR…

Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels between two images. Despite the tremendous progress of deep learning-based optical flow methods, it remains a challenge to accurately estimate…

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges…

Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores. Existing methods generally tackle this by hand-crafted or CNN-based methods, which either lack robustness to…

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

Recently, feature upsampling has gained increasing attention owing to its effectiveness in enhancing vision foundation models (VFMs) for pixel-level understanding tasks. Existing methods typically rely on high-resolution features from the…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark. Simply adjusting the brightness of a low-light…

When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or…

Currently, one main research line in designing a more efficient vision transformer is reducing the computational cost of self attention modules by adopting sparse attention or using local attention windows. In contrast, we propose a…

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Speech enhancement is a demanding task in automated speech processing pipelines, focusing on separating clean speech from noisy channels. Transformer based models have recently bested RNN and CNN models in speech enhancement, however at the…

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows…

In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…

We propose a cross-attention Transformer for joint decoding of uplink OFDM signals received by multiple coordinated access points. A shared per-receiver encoder learns the time-frequency structure of each grid, and a token-wise…