Related papers: FM-Fusion: Instance-aware Semantic Mapping Boosted…

We consider the problem of naming objects in complex, natural scenes containing widely varying object appearance and subtly different names. Informed by cognitive research, we propose an approach based on sharing context based object…

We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using…

Fine-grained multi-label classification models have broad applications in e-commerce, such as visual based label predictions ranging from fashion attribute detection to brand recognition. One challenge to achieve satisfactory performance…

Multi-sensor fusion in autonomous vehicles is becoming more common to offer a more robust alternative for several perception tasks. This need arises from the unique contribution of each sensor in collecting data: camera-radar fusion offers…

LiDAR-based 3D object detection presents significant challenges due to the inherent sparsity of LiDAR points. A common solution involves long-term temporal LiDAR data to densify the inputs. However, efficiently leveraging spatial-temporal…

Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a self-training method that utilizes fused multi-scale…

Recently, semi-supervised semantic segmentation has achieved promising performance with a small fraction of labeled data. However, most existing studies treat all unlabeled data equally and barely consider the differences and training…

In this paper, we propose a similarity-aware fusion network (SAFNet) to adaptively fuse 2D images and 3D point clouds for 3D semantic segmentation. Existing fusion-based methods achieve remarkable performances by integrating information…

Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited training data is available. While prior works usually…

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…

Semantic segmentation of multi-modal remote sensing imagery plays a pivotal role in land use/land cover (LULC) mapping, environmental monitoring, and precision earth observation. Current multi-modal approaches mainly focus on integrating…

The 3D scene understanding is mainly considered as a crucial requirement in computer vision and robotics applications. One of the high-level tasks in 3D scene understanding is semantic segmentation of RGB-Depth images. With the availability…

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these…

Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…

Quantitative measurement of crystals in high-resolution images allows for important insights into underlying material characteristics. Deep learning has shown great progress in vision-based automatic crystal size measurement, but current…

Single-point annotation in visual tasks, with the goal of minimizing labelling costs, is becoming increasingly prominent in research. Recently, visual foundation models, such as Segment Anything (SAM), have gained widespread usage due to…

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Infrared and visible image fusion is a powerful technique that combines complementary information from different modalities for downstream semantic perception tasks. Existing learning-based methods show remarkable performance, but are…

Feature fusion modules from encoder and self-attention module have been adopted in semantic segmentation. However, the computation of these modules is costly and has operational limitations in real-time environments. In addition,…

Depth completion plays a vital role in 3D perception systems, especially in scenarios where sparse depth data must be densified for tasks such as autonomous driving, robotics, and augmented reality. While many existing approaches rely on…