Related papers: Incrementally Zero-Shot Detection by an Extreme Va…

We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed method augments the state-of-the-art bilinear compatibility model…

Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to…

In this paper, we introduce VoteCut, an innovative method for unsupervised object discovery that leverages feature representations from multiple self-supervised models. VoteCut employs normalized-cut based graph partitioning, clustering and…

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However despite the increasing ubiquity of 3D sensors, the corresponding…

Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this work we tackle the…

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in…

To recognize objects of the unseen classes, most existing Zero-Shot Learning(ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then…

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…

This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a sample (e.g., an image) based on seen classes and auxiliary…

Zero-shot instance segmentation aims to detect and precisely segment objects of unseen categories without any training samples. Since the model is trained on seen categories, there is a strong bias that the model tends to classify all the…

In the process of exploring the world, the curiosity constantly drives humans to cognize new things. Supposing you are a zoologist, for a presented animal image, you can recognize it immediately if you know its class. Otherwise, you would…

While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is…

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and…

Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental…

Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, prompt learning has emerged…

Most of the existing Zero-Shot Learning (ZSL) methods focus on learning a compatibility function between the image representation and class attributes. Few others concentrate on learning image representation combining local and global…

Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data. However, existing ZSID systems suffer from two limitations: 1) They are not good at modeling the relationship between…

Few-shot object detection~(FSOD), which aims to detect novel objects with limited annotated instances, has made significant progress in recent years. However, existing methods still suffer from biased representations, especially for novel…

Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much. In this paper, we propose an…

Detecting AI-generated images has become an extraordinarily difficult challenge as new generative architectures emerge on a daily basis with more and more capabilities and unprecedented realism. New versions of many commercial tools, such…