Related papers: Macformer: Transformer with Random Maclaurin Featu…
Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…
The paper develops a Transformer architecture for estimating dynamic factors from multivariate time series data under flexible identification assumptions. Performance on small datasets is improved substantially by using a conventional…
Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view…
Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…
Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such systems. However, the…
Research in efficient vision backbones is evolving into models that are a mixture of convolutions and transformer blocks. A smart combination of both, architecture-wise and component-wise is mandatory to excel in the speedaccuracy…
In recent years, Transformer networks are beginning to replace pure convolutional neural networks (CNNs) in the field of computer vision due to their global receptive field and adaptability to input. However, the quadratic computational…
The Transformer model architecture has become one of the most widely used in deep learning and the attention mechanism is at its core. The standard attention formulation uses a softmax operation applied to a scaled dot product between query…
Pansharpening aims to combine a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image. Although pansharpening in the frequency domain offers clear…
The discovery of the lazy neuron phenomenon in trained Transformers, where the vast majority of neurons in their feed-forward networks (FFN) are inactive for each token, has spurred tremendous interests in activation sparsity for enhancing…
Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or…
Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance. We identify the root cause of this degradation as the…
The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision. However, a critical limitation of this model is its quadratic computational and memory complexity…
Transformers and large language models (LLMs), powered by the attention mechanism, have transformed numerous AI applications, driving the need for specialized hardware accelerators. A major challenge in these accelerators is efficiently…
Recently Transformer-based hyperspectral image (HSI) change detection methods have shown remarkable performance. Nevertheless, existing attention mechanisms in Transformers have limitations in local feature representation. To address this…
The transformer model is known to be computationally demanding, and prohibitively costly for long sequences, as the self-attention module uses a quadratic time and space complexity with respect to sequence length. Many researchers have…
Understanding user intent is essential for situational and context-aware decision-making. Motivated by a real-world scenario, this work addresses intent predictions of smart device users in the vicinity of vehicles by modeling sequential…
While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…
Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to learn visual representations, but these networks are spatially…
Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing, whose effectiveness is mainly attributed to its multi-head attention (MHA)…