Related papers: Fast SAM2 with Text-Driven Token Pruning

Localizing object parts precisely is essential for tasks such as object recognition and robotic manipulation. Recent part segmentation methods require extensive training data and labor-intensive annotations. Segment-Anything Model (SAM) has…

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…

Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decision-making. However, their real-world deployment is hindered by significant computational…

Extracting high-fidelity 2D contours from Scanning Electron Microscope (SEM) images is critical for calibrating Optical Proximity Correction (OPC) models. While foundation models like Segment Anything 2 (SAM2) are promising, adapting them…

As large-scale foundation models trained on billions of image--mask pairs covering a vast diversity of scenes, objects, and contexts, SAM and its upgraded version, SAM~2, have significantly influenced multiple fields within computer vision.…

Ultrasound (US) video segmentation remains a challenging problem due to strong inter- and intra-dataset variability, motion artifacts, and limited annotated data. Although foundation models such as Segment Anything Model 2 (SAM2)…

Segmenting 3D objects into parts is a long-standing challenge in computer vision. To overcome taxonomy constraints and generalize to unseen 3D objects, recent works turn to open-world part segmentation. These approaches typically transfer…

Segmentation of anatomical structures and pathological regions in medical images is essential for modern clinical diagnosis, disease research, and treatment planning. While significant advancements have been made in deep learning-based…

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens.…

Recent advancements in large foundation models have shown promising potential in the medical industry due to their flexible prompting capability. One such model, the Segment Anything Model (SAM), a prompt-driven segmentation model, has…

Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLLMs) have achieved strong performance on IVS, their inference…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Fire segmentation remains a critical challenge in computer vision due to flames' irregular boundaries, translucent edges, and highly variable intensities. While the Segment Anything Models (SAM and SAM2) have demonstrated impressive…

360 video object segmentation (360VOS) aims to predict temporally-consistent masks in 360 videos, offering full-scene coverage, benefiting applications, such as VR/AR and embodied AI. Learning 360VOS model is nontrivial due to the lack of…

Surgical video segmentation is crucial for computer-assisted surgery, enabling precise localization and tracking of instruments and tissues. Interactive Video Object Segmentation (iVOS) models such as Segment Anything Model 2 (SAM2) provide…

With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current…

Vision-language models (VLMs) excel at image understanding tasks, but the large number of visual tokens imposes significant computational costs, hindering deployment on mobile devices. Many pruning methods rely solely on token importance…

Segmentation is a fundamental task in computer vision, with prompt-driven methods gaining prominence due to their flexibility. The Segment Anything Model (SAM) excels at point-prompted segmentation, while text-based models, often leveraging…