Related papers: Prompt-based Dynamic Token Pruning for Efficient S…
Whole-body PET/CT is a cornerstone of oncological imaging, yet accurate lesion segmentation remains challenging due to tracer heterogeneity, physiological uptake, and multi-center variability. While fully automated methods have advanced…
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression. Our approach covers a wide range of compression rates with the assistance of the Layer-adaptive Prompt Module (LPM). Inspired…
Visual Language Models require substantial computational resources for inference due to the additional input tokens needed to represent visual information. However, these visual tokens often contain redundant and unimportant information,…
Vision Transformers (ViTs) have demonstrated state-ofthe-art performance in several benchmarks, yet their high computational costs hinders their practical deployment. Patch Pruning offers significant savings, but existing approaches…
In-context learning (ICL) with Large Vision Models (LVMs) presents a promising avenue in medical image segmentation by reducing the reliance on extensive labeling. However, the ICL performance of LVMs highly depends on the choices of visual…
The rapid growth of visual tokens in multimodal large language models (MLLMs) leads to excessive memory consumption and inference latency, especially when handling high-resolution images and videos. Token pruning is a technique used to…
Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging…
While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies.…
Interactive segmentation aims to extract objects of interest from an image based on user-provided clicks. In real-world applications, there is often a need to segment a series of images featuring the same target object. However, existing…
As deep neural networks are growing in size and being increasingly deployed to more resource-limited devices, there has been a recent surge of interest in network pruning methods, which aim to remove less important weights or activations of…
We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies…
Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…
Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token…
Segmentation is a fundamental problem in surgical scene analysis using artificial intelligence. However, the inherent data scarcity in this domain makes it challenging to adapt traditional segmentation techniques for this task. To tackle…
Visual prompting has emerged as a powerful method for adapting pre-trained models to new domains without updating model parameters. However, existing prompting methods typically optimize a single prompt per domain and apply it uniformly to…
Most advances in medical image recognition supporting clinical auxiliary diagnosis meet challenges due to the low-resource situation in the medical field, where annotations are highly expensive and professional. This low-resource problem…
Visual token reduction is critical for accelerating Vision-Language Models (VLMs), yet most existing approaches rely on a fixed budget shared across all inputs, overlooking the substantial variation in image information density. We propose…
Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction…
Prompt learning is an efficient approach to adapt transformers by inserting learnable set of parameters into the input and intermediate representations of a pre-trained model. In this work, we present Expressive Prompts with Residuals…
Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by the language model.…