Related papers: A Saccade-inspired Approach to Image Classificatio…

Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that learns the mapping between input images and output sequences…

One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses the entire sequence length, however, the actual attention being used is sparse. Humans…

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the…

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Photo collections and its applications today attempt to reflect user interactions in various forms. Moreover, photo collections aim to capture the users' intention with minimum effort through applications capturing user intentions. Human…

Visual attention is a fundamental mechanism in the human brain, and it inspires the design of attention mechanisms in deep neural networks. However, most of the visual attention studies adopted eye-tracking data rather than the direct…

Transformers have become prevalent in computer vision due to their performance and flexibility in modelling complex operations. Of particular significance is the 'cross-attention' operation, which allows a vector representation (e.g. of an…

Biomedical image analysis is of paramount importance for the advancement of healthcare and medical research. Although conventional convolutional neural networks (CNNs) are frequently employed in this domain, facing limitations in capturing…

Automatically generating a human-like description for a given image is a potential research in artificial intelligence, which has attracted a great of attention recently. Most of the existing attention methods explore the mapping…

Human attention is the gateway to conscious perception, memory and decision-making. However, its role in modern transformer models remains largely unexplored. As these systems increasingly influence what people see, prefer and buy, the…

Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches that rely on RNNs or stacked attention layers to refine…

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention…

The DINO family of self-supervised vision models has shown remarkable transferability, yet effectively adapting their representations for segmentation remains challenging. Existing approaches often rely on heavy decoders with multi-scale…

Recently, there have been explorations of generalist segmentation models that can effectively tackle a variety of image segmentation tasks within a unified in-context learning framework. However, these methods still struggle with task…

Since their introduction the Trasformer architectures emerged as the dominating architectures for both natural language processing and, more recently, computer vision applications. An intrinsic limitation of this family of "fully-attentive"…

Convolutional blocks have played a crucial role in advancing medical image segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.…

Modern machine learning models for computer vision exceed humans in accuracy on specific visual recognition tasks, notably on datasets like ImageNet. However, high accuracy can be achieved in many ways. The particular decision function…

Attention mechanisms have attracted considerable interest in image captioning because of its powerful performance. Existing attention-based models use feedback information from the caption generator as guidance to determine which of the…

A fine-grained account of functional selectivity in the cortex is essential for understanding how visual information is processed and represented in the brain. Classical studies using designed experiments have identified multiple…