相关论文: Reference-based Category Discovery: Unsupervised O…

Both indoor and outdoor scene perceptions are essential for embodied intelligence. However, current sparse supervised 3D object detection methods focus solely on outdoor scenes without considering indoor settings. To this end, we propose a…

This paper investigates the problem of image classification with limited or no annotations, but abundant unlabeled data. The setting exists in many tasks such as semi-supervised image classification, image clustering, and image retrieval.…

In this paper we tackle the problem of Generalized Category Discovery (GCD). Specifically, given a dataset with labelled and unlabelled images, the task is to cluster all images in the unlabelled subset, whether or not they belong to the…

Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples…

Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled data to improve the reliability of robotic vision systems in open-world environments. Previous approaches to UDA-OD based on self-training have been effective in…

We present ObjectBox, a novel single-stage anchor-free and highly generalizable object detection approach. As opposed to both existing anchor-based and anchor-free detectors, which are more biased toward specific object scales in their…

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised image segmentation, they significantly lag behind supervised models. In…

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have…

In recent years, deep learning technology has been maturely applied in the field of object detection, and most algorithms tend to be supervised learning. However, a large amount of labeled data requires high costs of human resources, which…

In this work, we tackle the challenging problem of category-level object pose and size estimation from a single depth image. Although previous fully-supervised works have demonstrated promising performance, collecting ground-truth pose…

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes. Given that knowledge learned…

Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into…

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel…

Semi-supervised object detection (SSOD) based on pseudo-labeling significantly reduces dependence on large labeled datasets by effectively leveraging both labeled and unlabeled data. However, real-world applications of SSOD often face…

This paper explores a novel setting called Generalized Category Discovery in Semantic Segmentation (GCDSS), aiming to segment unlabeled images given prior knowledge from a labeled set of base classes. The unlabeled images contain pixels of…

Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation…

In open-world scenarios, Generalized Category Discovery (GCD) requires identifying both known and novel categories within unlabeled data. However, existing methods often suffer from prototype confusion caused by shortcut learning, which…

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

Boundary and edge cues are highly beneficial in improving a wide variety of vision tasks such as semantic segmentation, object recognition, stereo, and object proposal generation. Recently, the problem of edge detection has been revisited…

In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical…