Related papers: A Unified Objective for Novel Class Discovery

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more…

Continuous category discovery (CCD) aims to automatically discover novel categories in continuously arriving unlabeled data. This is a challenging problem considering that there is no number of categories and labels in the newly arrived…

Open World Object Detection (OWOD) is a novel computer vision task with a considerable challenge, bridging the gap between classic object detection (OD) benchmarks and real-world object detection. In addition to detecting and classifying…

Learning to estimate object pose often requires ground-truth (GT) labels, such as CAD model and absolute-scale object pose, which is expensive and laborious to obtain in the real world. To tackle this problem, we propose an unsupervised…

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…

Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on a labeled source domain to an unlabeled target domain. State-of-the-art object Re-ID approaches adopt clustering algorithms to generate…

Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly…

Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets, providing a more realistic setting for image recognition. Essentially, GCD needs to remember existing patterns thoroughly…

Camouflaged Object Detection (COD) aims to identify objects that blend seamlessly into their surroundings. The inherent visual complexity of camouflaged objects, including their low contrast with the background, diverse textures, and subtle…

In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are…

Traditional one-shot detection methods have addressed the closed-set problem in object detection, but the high cost of data annotation remains a critical challenge. General unsupervised methods generate pseudo boxes without category labels,…

We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while…

The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision. Semi-Supervised Object Detection (SSOD) leverages a combination of a…

In this paper, we introduce a novel task termed unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typically treat anomaly…

Although a number of studies are devoted to novel category discovery, most of them assume a static setting where both labeled and unlabeled data are given at once for finding new categories. In this work, we focus on the application…

We tackle object category discovery, which is the problem of discovering and localizing novel objects in a large unlabeled dataset. While existing methods show results on datasets with less cluttered scenes and fewer object instances per…

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn…

Generalized category discovery (GCD) is an important and challenging task in open-world learning. Specifically, given some labeled data of known classes, GCD aims to cluster unlabeled data that contain both known and unknown classes.…

Object detection under imperfect data receives great attention recently. Weakly supervised object detection (WSOD) suffers from severe localization issues due to the lack of instance-level annotation, while semi-supervised object detection…

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in…