Related papers: VPNeXt -- Rethinking Dense Decoding for Plain Visi…

Monocular depth estimation (MDE) aims to infer per-pixel depth from a single RGB image. While diffusion models have advanced MDE with impressive generalization, they often exhibit limitations in accurately reconstructing far-range regions.…

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to…

Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally intensive and costly. To address this challenge, we introduce…

MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive state-of-the-art…

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a stack of self attention blocks. However, unlike Convolutional…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Secure multi-party computation (MPC) enables computation directly on encrypted data and protects both data and model privacy in deep learning inference. However, existing neural network architectures, including Vision Transformers (ViTs),…

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant…

Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential in various computer vision tasks. The wide deployment of ViT in real-world tasks requires a thorough understanding of the societal impact…

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on…

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…

Most polyp segmentation methods use CNNs as their backbone, leading to two key issues when exchanging information between the encoder and decoder: 1) taking into account the differences in contribution between different-level features and…

The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the…

Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias…

Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leveraging the prior knowledge of VFMs, we identify two…

A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection…

Vision Transformer (ViT) has achieved remarkable results in object detection for synthetic aperture radar (SAR) images, owing to its exceptional ability to extract global features. However, it struggles with the extraction of multi-scale…