Related papers: DART: Differentiable Dynamic Adaptive Region Token…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

We introduce Hybrid Autoregressive Transformer (HART), an autoregressive (AR) visual generation model capable of directly generating 1024x1024 images, rivaling diffusion models in image generation quality. Existing AR models face…

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

Foundation models (FMs) offer powerful representations for geospatial analysis, but adapting them effectively remains challenging. Standard adaptation methods, whether full fine-tuning or efficient frozen-backbone approaches, typically…

Vision Transformers (ViTs) have shown significant promise in computer vision applications. However, their performance in few-shot learning is limited by challenges in refining token-level interactions, struggling with limited training data,…

Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can…

We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address…

The emergence of vision transformers (ViTs) in image classification has shifted the methodologies for visual representation learning. In particular, ViTs learn visual representation at full receptive field per layer across all the image…

In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realistic results, most of them have difficulty handling…

High temporal resolution is essential for capturing fine-grained details in video understanding. However, current video large language models (VLLMs) and benchmarks mostly rely on low-frame-rate sampling, such as uniform sampling or…

The input tokens to Vision Transformers carry little semantic meaning as they are defined as regular equal-sized patches of the input image, regardless of its content. However, processing uniform background areas of an image should not…

There still remains an extreme performance gap between Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) when training from scratch on small datasets, which is concluded to the lack of inductive bias. In this paper, we…

Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chunking Diffusion…

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…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progress in fine-tuning VLMs but still face the challenges of…

Unsupervised domain adaptation (UDA) in videos is a challenging task that remains not well explored compared to image-based UDA techniques. Although vision transformers (ViT) achieve state-of-the-art performance in many computer vision…

Recent advances in vision-language modeling have produced promptable detection and segmentation systems that accept arbitrary natural language queries at inference time. Among these, SAM3 achieves state-of-the-art accuracy by combining a…

LiDAR-based 3D object detectors have been largely utilized in various applications, including autonomous vehicles or mobile robots. However, LiDAR-based detectors often fail to adapt well to target domains with different sensor…

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…