Related papers: The Missing Point in Vision Transformers for Unive…

With the rapid development of deep learning, CNN-based U-shaped networks have succeeded in medical image segmentation and are widely applied for various tasks. However, their limitations in capturing global features hinder their performance…

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational…

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an…

Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a…

The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…

The segmentation task has traditionally been formulated as a complete-label pixel classification task to predict a class for each pixel from a fixed number of predefined semantic categories shared by all images or videos. Yet, following…

Video tasks are compute-heavy and thus pose a challenge when deploying in real-time applications, particularly for tasks that require state-of-the-art Vision Transformers (ViTs). Several research efforts have tried to address this challenge…

The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT…

Generative models have shown a giant leap in synthesizing photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector…

Referring image segmentation is a fundamental vision-language task that aims to segment out an object referred to by a natural language expression from an image. One of the key challenges behind this task is leveraging the referring…

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the target mask with limited user inputs remains challenging. We…

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…

Recently, the vision transformer (ViT) has made breakthroughs in image recognition. Its self-attention mechanism (MSA) can extract discriminative labeling information of different pixel blocks to improve image classification accuracy.…

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Human vision is able to capture the part-whole hierarchical information from the entire scene. This paper presents the Visual Parser (ViP) that explicitly constructs such a hierarchy with transformers. ViP divides visual representations…

In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-standing and challenging inverse projection problem in vision, which we model as restoring the point clouds from perspective image sequences while…