Related papers: Dual Decision Improves Open-Set Panoptic Segmentat…

Existing open-world universal segmentation approaches usually leverage CLIP and pre-computed proposal masks to treat open-world segmentation tasks as proposal classification. However, 1) these works cannot handle universal segmentation in…

Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent…

Detecting obstacles in railway scenarios is both crucial and challenging due to the wide range of obstacle categories and varying ambient conditions such as weather and light. Given the impossibility of encompassing all obstacle categories…

Our work addresses the problem of learning to localize objects in an open-world setting, i.e., given the bounding box information of a limited number of object classes during training, the goal is to localize all objects, belonging to both…

A desirable open world recognition (OWR) system requires performing three tasks: (1) Open set recognition (OSR), i.e., classifying the known (classes seen during training) and rejecting the unknown (unseen$/$novel classes) online; (2)…

We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…

A consistent trend throughout the research of oriented object detection has been the pursuit of maintaining comparable performance with fewer and weaker annotations. This is particularly crucial in the remote sensing domain, where the dense…

3D object detection has been wildly studied in recent years, especially for robot perception systems. However, existing 3D object detection is under a closed-set condition, meaning that the network can only output boxes of trained classes.…

Autonomous driving (AD) operates in open-world scenarios, where encountering unknown objects is inevitable. However, standard object detectors trained on a limited number of base classes tend to ignore any unknown objects, posing potential…

Open-set active learning (OSAL) aims to identify informative samples for annotation when unlabeled data may contain previously unseen classes-a common challenge in safety-critical and open-world scenarios. Existing approaches typically rely…

The panoptic segmentation task requires a unified result from semantic and instance segmentation outputs that may contain overlaps. However, current studies widely ignore modeling overlaps. In this study, we aim to model overlap relations…

Open-set classification is a problem of handling `unknown' classes that are not contained in the training dataset, whereas traditional classifiers assume that only known classes appear in the test environment. Existing open-set classifiers…

Open-World Object Detection (OWOD) enriches traditional object detectors by enabling continual discovery and integration of unknown objects via human guidance. However, existing OWOD approaches frequently suffer from semantic confusion…

Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments. Previous approaches require full supervision on large-scale tabletop datasets for effective pretraining. In this paper, we…

In real-world applications, an object detector often encounters object instances from new classes and needs to accommodate them effectively. Previous work formulated this critical problem as incremental object detection (IOD), which assumes…

Unsupervised learning poses one of the most difficult challenges in computer vision today. The task has an immense practical value with many applications in artificial intelligence and emerging technologies, as large quantities of unlabeled…

Object proposals have become an integral preprocessing steps of many vision pipelines including object detection, weakly supervised detection, object discovery, tracking, etc. Compared to the learning-free methods, learning-based proposals…

Generalized Category Discovery (GCD) is a classification task that aims to classify both base and novel classes in unlabeled images, using knowledge from a labeled dataset. In GCD, previous research overlooks scene information or treats it…

Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies…

Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: severe cross-deployment domain shift, scarce or unavailable labels at new sites, and limited…