Related papers: Adaptive Token Sampling For Efficient Vision Trans…
This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series…
Advancements in computer vision research have put transformer architecture as the state of the art in computer vision tasks. One of the known drawbacks of the transformer architecture is the high number of parameters, this can lead to a…
Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…
Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current…
Vision Transformers rely on positional embeddings and class tokens encoding fixed spatial priors. While effective for natural images, these priors may be suboptimal when spatial layout is weakly informative, a frequent condition in medical…
Vision Transformers (ViTs) have emerged as a foundational model in computer vision, excelling in generalization and adaptation to downstream tasks. However, deploying ViTs to support diverse resource constraints typically requires…
Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and…
Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…
Existing models that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on convolution operations conditioned with feature-wise linear modulation (FiLM) layers. These layers require many new…
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…
\textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To address…
In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…
Vision Mamba has emerged as a strong competitor to Vision Transformers (ViTs) due to its ability to efficiently capture long-range dependencies with linear computational complexity. While token reduction, an effective compression technique…
The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies…
Vision Transformers (ViTs) have underpinned the recent breakthroughs in computer vision. However, designing the architectures of ViTs is laborious and heavily relies on expert knowledge. To automate the design process and incorporate…
Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, considering the practical constraints of computational and storage costs. Low-rank adaptation (LoRA) is a…
Test-Time Adaptation (TTA) has emerged as an effective solution for adapting Vision Transformers (ViT) to distribution shifts without additional training data. However, existing TTA methods often incur substantial computational overhead,…
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-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…
The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…