相关论文: Learning Pseudo-Labeler beyond Noun Concepts for O…

Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-category objects as…

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.…

New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either…

Recognising objects according to a pre-defined fixed set of class labels has been well studied in the Computer Vision. There are a great many practical applications where the subjects that may be of interest are not known beforehand, or so…

Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent methods show great progress in that direction, proper…

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Class-agnostic object detection (OD) can be a cornerstone or a bottleneck for many downstream vision tasks. Despite considerable advancements in bottom-up and multi-object discovery methods that leverage basic visual cues to identify…

Vision-Language Pre-training (VLP) with large-scale image-text pairs has demonstrated superior performance in various fields. However, the image-text pairs co-occurrent on the Internet typically lack explicit alignment information, which is…

Domain adaptation tackles the challenge of generalizing knowledge acquired from a source domain to a target domain with different data distributions. Traditional domain adaptation methods presume that the classes in the source and target…

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…

Open-vocabulary object detection (OVD) aims to detect objects beyond the training annotations, where detectors are usually aligned to a pre-trained vision-language model, eg, CLIP, to inherit its generalizable recognition ability so that…

In perception for automated vehicles, safety is critical not only for the driver but also for other agents in the scene, particularly vulnerable road users such as pedestrians and cyclists. Previous representation methods, such as Bird's…

Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly…

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…

In this work, we tackle the limitations of current LiDAR-based 3D object detection systems, which are hindered by a restricted class vocabulary and the high costs associated with annotating new object classes. Our exploration of…

Open-vocabulary object detection, which is concerned with the problem of detecting novel objects guided by natural language, has gained increasing attention from the community. Ideally, we would like to extend an open-vocabulary detector…

Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-language conceptual systems inspired by infants' word learning…

Open-world object detection (OWOD), as a more general and challenging goal, requires the model trained from data on known objects to detect both known and unknown objects and incrementally learn to identify these unknown objects. The…

Developing robot perception systems for recognizing objects in the real-world requires computer vision algorithms to be carefully scrutinized with respect to the expected operating domain. This demands large quantities of ground truth data…

Open-vocabulary semantic segmentation (OVSS) extends traditional closed-set segmentation by enabling pixel-wise annotation for both seen and unseen categories using arbitrary textual descriptions. While existing methods leverage…