Related papers: Annotation-free Audio-Visual Segmentation

Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3D domains. However, these approaches often require prior…

Training-free open-vocabulary semantic segmentation (OVS) aims to segment images given a set of arbitrary textual categories without costly model fine-tuning. Existing solutions often explore attention mechanisms of pre-trained models, such…

We introduce ASIA (Adaptive 3D Segmentation using few Image Annotations), a novel framework that enables segmentation of possibly non-semantic and non-text-describable "parts" in 3D. Our segmentation is controllable through a few…

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accuracy often falls…

Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes. Traditional methods address this by sequentially connecting a powerful mask proposal generator, such as the Segment…

Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these…

The Segment Anything Model (SAM) is a recently proposed prompt-based segmentation model in a generic zero-shot segmentation approach. With the zero-shot segmentation capacity, SAM achieved impressive flexibility and precision on various…

The Segment Anything Model (SAM) represents a significant breakthrough into foundation models for computer vision, providing a large-scale image segmentation model. However, despite SAM's zero-shot performance, its segmentation masks lack…

Vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been…

The emerging scale segmentation model, Segment Anything (SAM), exhibits impressive capabilities in zero-shot segmentation for natural images. However, when applied to medical images, SAM suffers from noticeable performance drop. To make SAM…

In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentation, namely AVS and RVOS tasks. The intuitive solution…

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…

Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently…

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Entity Segmentation (ES) aims at identifying and segmenting distinct entities within an image without the need for predefined class labels. This characteristic makes ES well-suited to open-world applications with adaptation to diverse and…

Accurate segmentation of anatomical structures in ultrasound (US) images, particularly small ones, is challenging due to noise and variability in imaging conditions (e.g., probe position, patient anatomy, tissue characteristics and…

This work focuses on multi-shot semi-supervised video object segmentation (MVOS), which aims at segmenting the target object indicated by an initial mask throughout a video with multiple shots. The existing VOS methods mainly focus on…

Point cloud data labeling is considered a time-consuming and expensive task in autonomous driving, whereas annotation-free learning training can avoid it by learning point cloud representations from unannotated data. In this paper, we…

We propose Semantic-Fast-SAM (SFS), a semantic segmentation framework that combines the Fast Segment Anything model with a semantic labeling pipeline to achieve real-time performance without sacrificing accuracy. FastSAM is an efficient…

Video Instance Segmentation (VIS) aims at segmenting and categorizing objects in videos from a closed set of training categories, lacking the generalization ability to handle novel categories in real-world videos. To address this…