相关论文: SeTformer is What You Need for Vision and Language

Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechanisms. Recent multi-modal diffusion transformers extend this…

Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense…

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

We introduce VistaFormer, a lightweight Transformer-based model architecture for the semantic segmentation of remote-sensing images. This model uses a multi-scale Transformer-based encoder with a lightweight decoder that aggregates global…

Since the introduction of Vision Transformers, the landscape of many computer vision tasks (e.g., semantic segmentation), which has been overwhelmingly dominated by CNNs, recently has significantly revolutionized. However, the computational…

Weakly supervised semantic segmentation (WSSS) must learn dense masks from noisy, under-specified cues. We revisit the SegFormer decoder and show that three small, synergistic changes make weak supervision markedly more effective-without…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

Multi-head-self-attention (MHSA)-equipped models have achieved notable performance in computer vision. Their computational complexity is proportional to quadratic numbers of pixels in input feature maps, resulting in slow processing,…

Following the tremendous success of transformer in natural language processing and image understanding tasks, in this paper, we present a novel point cloud representation learning architecture, named Dual Transformer Network (DTNet), which…

Fine-tuning pre-trained transformer models, e.g., Swin Transformer, are successful in numerous downstream for dense prediction vision tasks. However, one major issue is the cost/storage of their huge amount of parameters, which becomes…

The Vision Transformer (ViT) has demonstrated state-of-the-art performance in various computer vision tasks, but its high computational demands make it impractical for edge devices with limited resources. This paper presents MicroViT, a…

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often…

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…

Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…

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.…

Semantic segmentation of remotely sensed urban scene images is required in a wide range of practical applications, such as land cover mapping, urban change detection, environmental protection, and economic assessment.Driven by rapid…

Diffusion Transformers (DiTs) achieve state-of-the-art performance in text-to-image synthesis but remain computationally expensive due to the iterative nature of denoising and the quadratic cost of global attention. In this work, we observe…