相关论文: Bridging The Gaps Between Token Pruning and Full P…

High runtime memory and high latency puts significant constraint on Vision Transformer training and inference, especially on edge devices. Token pruning reduces the number of input tokens to the ViT based on importance criteria of each…

Medical image segmentation is a vital healthcare endeavor requiring precise and efficient models for appropriate diagnosis and treatment. Vision transformer (ViT)-based segmentation models have shown great performance in accomplishing this…

Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to reduce ViT's $O(n^2)$ complexity by pruning unimportant…

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight and token pruning are…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation.…

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still…

Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…

Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt…

Many recent inpainting works have achieved impressive results by leveraging Deep Neural Networks (DNNs) to model various prior information for image restoration. Unfortunately, the performance of these methods is largely limited by the…

Visual token compression is critical for Large Vision-Language Models (LVLMs) to efficiently process high-resolution inputs. Existing methods that typically adopt fixed compression ratios cannot adapt to scenes of varying complexity, often…

The widespread availability of pre-trained vision models has enabled numerous deep learning applications through their transferable representations. However, their computational and storage costs often limit practical deployment.…

Large Vision-Language Models (LVLMs) have shown impressive performance across multi-modal tasks by encoding images into thousands of tokens. However, the large number of image tokens results in significant computational overhead, and the…

Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of…

Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during…

Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that…

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image…

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…