相关论文: TIDE: Test Time Few Shot Object Detection

Few-shot object detection is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data. Its performance is largely affected by the data scarcity of novel classes. But the semantic relation between…

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…

Few-shot Open-set Object Detection (FOOD) poses a challenge in many open-world scenarios. It aims to train an open-set detector to detect known objects while rejecting unknowns with scarce training samples. Existing FOOD methods are subject…

While state-of-the-art general object detectors are getting better and better, there are not many systems specifically designed to take advantage of the instance detection problem. For many applications, such as household robotics, a system…

Viewpoint estimation for known categories of objects has been improved significantly thanks to deep networks and large datasets, but generalization to unknown categories is still very challenging. With an aim towards improving performance…

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…

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…

Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures…

We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification…

Object detection has made great progress in the past few years along with the development of deep learning. However, most current object detection methods are resource hungry, which hinders their wide deployment to many resource restricted…

This paper investigates a valuable setting called few-shot unsupervised domain adaptation (FS-UDA), which has not been sufficiently studied in the literature. In this setting, the source domain data are labelled, but with few-shot per…

Source-Free Object Detection (SFOD) has garnered much attention in recent years by eliminating the need of source-domain data in cross-domain tasks, but existing SFOD methods suffer from the Source Bias problem, i.e. the adapted model…

Open-vocabulary object detection (OVD), detecting specific classes of objects using only their linguistic descriptions (e.g., class names) without any image samples, has garnered significant attention. However, in real-world applications,…

Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited training data is available. While prior works usually…

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research…

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection…

Few-Shot Recognition (FSR) tackles classification tasks by training with minimal task-specific labeled data. Prevailing methods adapt or finetune a pretrained Vision-Language Model (VLM) and augment the scarce training data by retrieving…

Traditional shape descriptors have been gradually replaced by convolutional neural networks due to their superior performance in feature extraction and classification. The state-of-the-art methods recognize object shapes via image…

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…

Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and…