Related papers: Few-Example Object Detection with Model Communicat…

Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world…

In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vision. In a first…

Industrial object detection systems typically rely on large annotated datasets, which are expensive to collect and challenging to maintain in industrial scenarios where the inventory of objects changes frequently. This work addresses the…

Most currently used object detection methods are learning-based, and can detect objects under varying appearances. Those models require training and a training dataset. We focus on use cases with less data variation, but the requirement of…

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…

We address the problem of localisation of objects as bounding boxes in images and videos with weak labels. This weakly supervised object localisation problem has been tackled in the past using discriminative models where each object class…

In this paper, we consider a challenging but realistic continual learning (CL) problem, Few-Shot Continual Active Learning (FoCAL), where a CL agent is provided with unlabeled data for a new or a previously learned task in each increment…

Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer…

Few-shot object detection, learning to adapt to the novel classes with a few labeled data, is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data and the urgent demands to cut costs of data…

In the domain of Few-Shot Image Classification, operating with as little as one example per class, the presence of image ambiguities stemming from multiple objects or complex backgrounds can significantly deteriorate performance. Our…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances. The existing methods severely suffer from bias classification…

The success of existing salient object detection models relies on a large pixel-wise labeled training dataset, which is time-consuming and expensive to obtain. We study semi-supervised salient object detection, with access to a small number…

We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria…

Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. This could help scaling detection models to larger number of classes with fewer…

We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation…

Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region…

Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with different categories to improve the accuracy of few-shot…

Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…

Class-agnostic counting (CAC) has numerous potential applications across various domains. The goal is to count objects of an arbitrary category during testing, based on only a few annotated exemplars. In this paper, we point out that the…