Related papers: TASeg: Text-aware RGB-T Semantic Segmentation base…

Open-vocabulary semantic segmentation aims to segment images into distinct semantic regions for both seen and unseen categories at the pixel level. Current methods utilize text embeddings from pre-trained vision-language models like CLIP…

Vision-Language Models (VLMs) have shown remarkable potential in advancing autonomous driving by leveraging multi-modal fusion in order to enhance scene perception, reasoning, and decision-making. Despite their potential, existing models…

In the realm of artificial intelligence, the emergence of foundation models, backed by high computing capabilities and extensive data, has been revolutionary. Segment Anything Model (SAM), built on the Vision Transformer (ViT) model with…

The rapid development of deep learning has significantly improved salient object detection (SOD) combining both RGB and thermal (RGB-T) images. However, existing Transformer-based RGB-T SOD models with quadratic complexity are…

We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning-based instance segmentation and…

Segment Anything Model (SAM) has attracted widespread attention for its superior interactive segmentation capabilities with visual prompts while lacking further exploration of text prompts. In this paper, we empirically investigate what…

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS) has emerged as a solution to alleviate the labeling burden…

Multimodal 3D MRI brain tumor segmentation is a pivotal step in radiotherapy target delineation, surgical planning and post-treatment assessment. Existing methods often assume artifact-free MRI images. However, inevitable patient motion…

When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we investigate simple, yet effective approaches for adapting the…

Scribble supervised salient object detection (SSSOD) constructs segmentation ability of attractive objects from surroundings under the supervision of sparse scribble labels. For the better segmentation, depth and thermal infrared modalities…

Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced architectures to facilitate effective audio-visual interactions,…

Building a unified model with a single set of parameters to efficiently handle diverse types of medical lesion segmentation has become a crucial objective for AI-assisted diagnosis. Existing unified segmentation approaches typically rely on…

Reconstruction dynamic visual scenes from electroencephalography (EEG) signals remains a primary challenge in brain decoding, limited by the low spatial resolution of EEG, a temporal mismatch between neural recordings and video dynamics,…

Semantic Segmentation (SS) is promising for outdoor scene perception in safety-critical applications like autonomous vehicles, assisted navigation and so on. However, traditional SS is primarily based on RGB images, which limits the…

Online segmentation of laser-induced damage on large-aperture optics in high-power laser facilities is challenged by complicated damage morphology, uneven illumination and stray light interference. Fully supervised semantic segmentation…

Semantic segmentation of city-scale point clouds is a critical technology for Unmanned Aerial Vehicle (UAV) perception systems, enabling the classification of 3D points without relying on any visual information to achieve comprehensive 3D…

Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has also seen great interest. In this paper, we propose a…

For semantic segmentation in urban scene understanding, RGB cameras alone often fail to capture a clear holistic topology in challenging lighting conditions. Thermal signal is an informative additional channel that can bring to light the…

Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic segmentation is one the essential components of environmental…