Related papers: Multiple instance active learning for object detec…

In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models. Previous semi-supervised methods based on pseudo labels are…

Identifying moving objects is a crucial capability for autonomous navigation, consistent map generation, and future trajectory prediction of objects. In this paper, we propose a novel network that addresses the challenge of segmenting…

Instance detection (InsDet) is a long-lasting problem in robotics and computer vision, aiming to detect object instances (predefined by some visual examples) in a cluttered scene. Despite its practical significance, its advancement is…

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area…

Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…

Recent works on predictive uncertainty estimation have shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. However, these methods struggle to precisely locate the point of interest in the image, i.e,…

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple…

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…

Object detection traditionally relies on fixed category sets, requiring costly re-training to handle novel objects. While Open-World and Open-Vocabulary Object Detection (OWOD and OVOD) improve flexibility, OWOD lacks semantic labels for…

Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances. Current MIML solutions still focus on a single-type of objects and…

What constitutes an object? This has been a long-standing question in computer vision. Towards this goal, numerous learning-free and learning-based approaches have been developed to score objectness. However, they generally do not scale…

Open World Object Detection (OWOD), simulating the real dynamic world where knowledge grows continuously, attempts to detect both known and unknown classes and incrementally learn the identified unknown ones. We find that although the only…

In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object…

Nowadays, users demand for increased personalization of vision systems to localize and identify personal instances of objects (e.g., my dog rather than dog) from a few-shot dataset only. Despite outstanding results of deep networks on…

Without the demand of training in reality, humans can easily detect a known concept simply based on its language description. Empowering deep learning with this ability undoubtedly enables the neural network to handle complex vision tasks,…

Traditional object detection methods operate under the closed-set assumption, where models can only detect a fixed number of objects predefined in the training set. Recent works on open vocabulary object detection (OVD) enable the detection…

Much of the focus in the object detection literature has been on the problem of identifying the bounding box of a particular class of object in an image. Yet, in contexts such as robotics and augmented reality, it is often necessary to find…

Multiple object tracking (MOT) is a crucial task in computer vision society. However, most tracking-by-detection MOT methods, with available detected bounding boxes, cannot effectively handle static, slow-moving and fast-moving camera…

LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience…

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…