Related papers: Label Space Partition Selection for Multi-Object T…

In this paper, we investigate the use of an unsupervised label clustering technique and demonstrate that it enables substantial improvements in visual relationship prediction accuracy on the Person in Context (PIC) dataset. We propose to…

In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…

Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification…

In multi-object inference, the multi-object probability density captures the uncertainty in the number and the states of the objects as well as the statistical dependence between the objects. Exact computation of the multi-object density is…

Symmetries of combinatorial objects are known to complicate search algorithms, but such obstacles can often be removed by detecting symmetries early and discarding symmetric subproblems. Canonical labeling of combinatorial objects…

High-resolution radar sensors are critical for autonomous systems but pose significant challenges to traditional tracking algorithms due to the generation of multiple measurements per object and the presence of multipath effects. Existing…

Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing…

Adaptive tracking-by-detection approaches are popular for tracking arbitrary objects. They treat the tracking problem as a classification task and use online learning techniques to update the object model. However, these approaches are…

Label propagation is a popular technique for anatomical segmentation. In this work, we propose a novel deep framework for label propagation based on non-local label fusion. Our framework, named CompareNet, incorporates subnets for both…

Multi-label classification has attracted an increasing amount of attention in recent years. To this end, many algorithms have been developed to classify multi-label data in an effective manner. However, they usually do not consider the…

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…

Multi-target state estimation refers to estimating the number of targets and their trajectories in a surveillance area using measurements contaminated with noise and clutter. In the Bayesian paradigm, the most common approach to…

Recently, detection of label errors and improvement of label quality in datasets for supervised learning tasks has become an increasingly important goal in both research and industry. The consequences of incorrectly annotated data include…

Image classification is a challenging problem for computer in reality. Large numbers of methods can achieve satisfying performances with sufficient labeled images. However, labeled images are still highly limited for certain image…

Graph database is designed to store bidirectional relationships between objects and facilitate the traversal process to extract a subgraph. However, the subgraph matching process is an NP-Complete problem. Existing solutions to this problem…

As datasets grow it becomes infeasible to process them completely with a desired model. For giant datasets, we frame the order in which computation is performed as a decision problem. The order is designed so that partial computations are…

Graph clustering has many important applications in computing, but due to growing sizes of graphs, even traditionally fast clustering methods such as spectral partitioning can be computationally expensive for real-world graphs of interest.…

Traversability estimation is critical for enabling robots to navigate across diverse terrains and environments. While recent self-supervised learning methods achieve promising results, they often fail to capture the characteristics of…

We present a method for training multi-label, massively multi-class image classification models, that is faster and more accurate than supervision via a sigmoid cross-entropy loss (logistic regression). Our method consists in embedding…

Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation and…