相关论文: Linear Attention with Global Context: A Multipole …

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP)…

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

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)…

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set,…

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that…

While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a…

Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents. Existing state-of-the-art approaches use…

Recent work has shown the potential of transformers for computer vision applications. An image is first partitioned into patches, which are then used as input tokens for the attention mechanism. Due to the expensive quadratic cost of the…

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Learning semantically meaningful image transformations (i.e. rotation, thickness, blur) directly from examples can be a challenging task. Recently, the Manifold Autoencoder (MAE) proposed using a set of Lie group operators to learn image…

Attention is fundamental to cognition, yet it remains a challenge to understand attention in tasks approaching real-world complexity. Here, we approached this problem by modeling gaze patterns of monkeys playing Pac-Man. We first show a…

Multimodal learning models have become increasingly important as they surpass single-modality approaches on diverse tasks ranging from question-answering to autonomous driving. Despite the importance of multimodal learning, existing efforts…

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Ever since their conception, Transformers have taken over traditional sequence models in many tasks, such as NLP, image classification, and video/audio processing, for their fast training and superior performance. Much of the merit is…

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…