Related papers: Deep Deterministic Uncertainty for Semantic Segmen…
This paper introduces a novel approach to 4D Panoptic LiDAR Segmentation that decouples semantic and instance segmentation, leveraging single-scan semantic predictions as prior information for instance segmentation. Our method D-PLS first…
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo…
Generative diffusion models, notable for their large parameter count (exceeding 100 million) and operation within high-dimensional image spaces, pose significant challenges for traditional uncertainty estimation methods due to computational…
Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple…
We introduce ProPanDL, a family of networks capable of uncertainty-aware panoptic segmentation. Unlike existing segmentation methods, ProPanDL is capable of estimating full probability distributions for both the semantic and spatial aspects…
Dense prediction tasks are common for 3D point clouds, but the uncertainties inherent in massive points and their embeddings have long been ignored. In this work, we present CUE, a novel uncertainty estimation method for dense prediction…
This paper addresses semantic image segmentation by incorporating rich information into Markov Random Field (MRF), including high-order relations and mixture of label contexts. Unlike previous works that optimized MRFs using iterative…
Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful…
Semantic segmentation has achieved remarkable results with high computational cost and a large number of parameters. However, real-world applications require efficient inference speed on embedded devices. Most previous works address the…
Virtual Diagnostic (VD) is a computational tool based on deep learning that can be used to predict a diagnostic output. VDs are especially useful in systems where measuring the output is invasive, limited, costly or runs the risk of…
The process of segmenting point cloud data into several homogeneous areas with points in the same region having the same attributes is known as 3D segmentation. Segmentation is challenging with point cloud data due to substantial…
The design of neural network architectures is an important component for achieving state-of-the-art performance with machine learning systems across a broad array of tasks. Much work has endeavored to design and build architectures…
While deep neural networks have become the go-to approach in computer vision, the vast majority of these models fail to properly capture the uncertainty inherent in their predictions. Estimating this predictive uncertainty can be crucial,…
We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations. Contrary to existing approaches posing semantic segmentation as a single task of region-based classification, our…
Indoor scenes are usually characterized by scattered objects and their relationships, which turns the indoor scene classification task into a challenging computer vision task. Despite the significant performance boost in classification…
Active learning aims to reduce labeling costs by selecting only the most informative samples on a dataset. Few existing works have addressed active learning for object detection. Most of these methods are based on multiple models or are…
We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative paradigm for prediction by progressively removing noise from a…
The state-of-the-art object detection and image classification methods can perform impressively on more than 9k and 10k classes, respectively. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This…
In view of the problems that existing salient object detection (SOD) methods are prone to losing details, blurring edges, and insufficient fusion of single-modal information in complex scenes, this paper proposes a dynamic uncertainty…
Deep learning based methods for automatic organ segmentation have shown promise in aiding diagnosis and treatment planning. However, quantifying and understanding the uncertainty associated with model predictions is crucial in critical…