Related papers: Few-shot Object Detection in Remote Sensing: Lifti…
Few-shot object detection (FSOD) aims to detect objects with limited samples for novel classes, while relying on abundant data for base classes. Existing FSOD approaches, predominantly built on the Faster R-CNN detector, entangle objectness…
Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species…
Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain…
The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from…
Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches…
Cross-modal feature extraction and integration have led to steady performance improvements in few-shot learning tasks due to generating richer features. However, existing multi-modal object detection (MM-OD) methods degrade when facing…
Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited training data makes it difficult to represent the data distribution of realistic remote…
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…
Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images. However, when there exists a domain gap between the base and novel classes, the state-of-the-art FSS methods…
In this paper, we present FSOD-VFM: Few-Shot Object Detectors with Vision Foundation Models, a framework that leverages vision foundation models to tackle the challenge of few-shot object detection. FSOD-VFM integrates three key components:…
Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and efficiency. Most…
Recently, the field of few-shot detection within remote sensing imagery has witnessed significant advancements. Despite these progresses, the capacity for continuous conceptual learning still poses a significant challenge to existing…
Recent studies have used unsupervised domain adaptive object detection (UDAOD) methods to bridge the domain gap in remote sensing (RS) images. However, UDAOD methods typically assume that the source domain data can be accessed during the…
Vision-based industrial inspection (VII) aims to locate defects quickly and accurately. Supervised learning under a close-set setting and industrial anomaly detection, as two common paradigms in VII, face different problems in practical…
Cross-domain few-shot object detection (CD-FSOD) aims to adapt pretrained detectors from a source domain to target domains with limited annotations, suffering from severe domain shifts and data scarcity problems. In this work, we find a…
Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficient, thereby failing to meet the requirements for realworld…
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…
Most existing object detection methods rely on the availability of abundant labelled training samples per class and offline model training in a batch mode. These requirements substantially limit their scalability to open-ended accommodation…
In this work, we address the problem of few-shot multi-class object counting with point-level annotations. The proposed technique leverages a class agnostic attention mechanism that sequentially attends to objects in the image and extracts…
In remote sensing field, there are many applications of object detection in recent years, which demands a great number of labeled data. However, we may be faced with some cases where only limited data are available. In this paper, we…