相关论文: Mechanisms of Non-Monotonic Scaling in Vision Tran…

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…

A surge of interest has emerged in utilizing Transformers in diverse vision tasks owing to its formidable performance. However, existing approaches primarily focus on optimizing internal model architecture designs that often entail…

Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on…

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…

Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe that smaller ViTs are intrinsically the sub-networks of a…

Current researches indicate that inductive bias (IB) can improve Vision Transformer (ViT) performance. However, they introduce a pyramid structure concurrently to counteract the incremental FLOPs and parameters caused by introducing IB.…

We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision…

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than…

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e.,…

The computational overhead of Vision Transformers in practice stems fundamentally from their deep architectures, yet existing acceleration strategies have primarily targeted algorithmic-level optimizations such as token pruning and…

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture…

Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance and high data efficiency in recent research. However,…

Despite widespread adoption, multimodal large language models (MLLMs) suffer performance degradation when encountering unfamiliar queries under distribution shifts. Existing methods to improve MLLM generalization typically require either…

The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range…

The recent success of Vision Transformers has generated significant interest in attention mechanisms and transformer architectures. Although existing methods have proposed spiking self-attention mechanisms compatible with spiking neural…

Vision Transformers (ViTs) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant…

Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how much can be realized through recurrent computation. We study…

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…