Related papers: TransNeXt: Robust Foveal Visual Perception for Vis…

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible…

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

Deep learning architectures are an extremely powerful tool for recognizing and classifying images. However, they require supervised learning and normally work on vectors the size of image pixels and produce the best results when trained on…

Deepfakes, which employ GAN to produce highly realistic facial modification, are widely regarded as the prevailing method. Traditional CNN have been able to identify bogus media, but they struggle to perform well on different datasets and…

Transformer-based methods for RGB-D Salient Object Detection (SOD) have gained significant interest, owing to the transformer's exceptional capacity to capture long-range pixel dependencies. Nevertheless, current RGB-D SOD methods face…

This paper proposes an Agile Aggregating Multi-Level feaTure framework (Agile Amulet) for salient object detection. The Agile Amulet builds on previous works to predict saliency maps using multi-level convolutional features. Compared to…

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…

Convolutional Neural Networks (CNNs) and Transformers have achieved remarkable success in computer vision tasks. However, their deep architectures often lead to high computational redundancy, making them less suitable for…

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of…

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to…

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Image description generation is essential for accessibility and AI understanding of visual content. Recent advancements in deep learning have significantly improved natural language processing and computer vision. In this work, we propose…

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model. A vanilla ViT, on the other hand, faces difficulties…

Modern diffusion models, particularly those utilizing a Transformer-based UNet for denoising, rely heavily on self-attention operations to manage complex spatial relationships, thus achieving impressive generation performance. However, this…

Transformer attention architectures, similar to those developed for natural language processing, have recently proved efficient also in vision, either in conjunction with or as a replacement for convolutional layers. Typically, visual…

Deepfakes have raised significant concerns due to their potential to spread false information and compromise digital media integrity. Current deepfake detection models often struggle to generalize across a diverse range of deepfake…

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers…