Related papers: Blending Anti-Aliasing into Vision Transformer

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword…

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Although Vision Transformers (ViTs) have become the standard architecture in computer vision, their massive sizes lead to significant computational overhead. Token compression techniques have attracted considerable attention to address this…

Transformers were initially introduced for natural language processing (NLP) tasks, but fast they were adopted by most deep learning fields, including computer vision. They measure the relationships between pairs of input tokens (words in…

"Lightweight convolutional neural networks" is an important research topic in the field of embedded vision. To implement image recognition tasks on a resource-limited hardware platform, it is necessary to reduce the memory size and the…

Anomaly detection and localization in images is a growing field in computer vision. In this area, a seemingly understudied problem is anomaly clustering, i.e., identifying and grouping different types of anomalies in a fully unsupervised…

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…

The audio-visual speech fusion strategy AV Align has shown significant performance improvements in audio-visual speech recognition (AVSR) on the challenging LRS2 dataset. Performance improvements range between 7% and 30% depending on the…

Empowered by transformer-based models, visual tracking has advanced significantly. However, the slow speed of current trackers limits their applicability on devices with constrained computational resources. To address this challenge, we…

We address the problem of solving mixed random linear equations. We have unlabeled observations coming from multiple linear regressions, and each observation corresponds to exactly one of the regression models. The goal is to learn the…

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability. However, the pairwise token affinity and complex matrix operations limit its deployment on…

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Transformers have recently gained increasing attention in computer vision. However, existing studies mostly use Transformers for feature representation learning, e.g. for image classification and dense predictions, and the generalizability…

Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of vision tasks recently. While achieving excellent performance, they still require relatively intensive computational cost…

Pose variation is one of the key challenges in face recognition. Conventional techniques mainly focus on face frontalization or face augmentation in image space. However, transforming face images in image space is not guaranteed to preserve…

To overcome the poor scalability of convolutional neural network, recurrent attention model(RAM) selectively choose what and where to look on the image. By directing recurrent attention model how to look the image, RAM can be even more…