English
Related papers

Related papers: IntraQ: Learning Synthetic Images with Intra-Class…

200 papers

Zero-shot learning deals with the ability to recognize objects without any visual training sample. To counterbalance this lack of visual data, each class to recognize is associated with a semantic prototype that reflects the essential…

Computer Vision and Pattern Recognition · Computer Science 2021-02-08 Yannick Le Cacheux , Hervé Le Borgne , Michel Crucianu

Zero-shot learning (ZSL) which aims to recognize unseen classes with no labeled training sample, efficiently tackles the problem of missing labeled data in image retrieval. Nowadays there are mainly two types of popular methods for ZSL to…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Gang Yang , Jinlu Liu , Xirong Li

In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Zhi Chen , Yadan Luo , Zi Huang , Jingjing Li , Sen Wang , Xin Yu

Quantization techniques applied to the inference of deep neural networks have enabled fast and efficient execution on resource-constraint devices. The success of quantization during inference has motivated the academic community to explore…

Machine Learning · Computer Science 2021-05-11 Marios Fournarakis , Markus Nagel

Zero-shot learning (ZSL) is commonly used to address the very pervasive problem of predicting unseen classes in fine-grained image classification and other tasks. One family of solutions is to learn synthesised unseen visual samples…

Computer Vision and Pattern Recognition · Computer Science 2020-08-10 Zhi Chen , Sen Wang , Jingjing Li , Zi Huang

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to…

Computer Vision and Pattern Recognition · Computer Science 2017-10-16 Yanwei Fu , Tao Xiang , Yu-Gang Jiang , Xiangyang Xue , Leonid Sigal , Shaogang Gong

Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically related unseen classes, which are absent during training. The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned…

Artificial Intelligence · Computer Science 2021-12-30 Yun Li , Zhe Liu , Lina Yao , Xiaojun Chang

Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing algorithm should localize and recover affected regions while…

Computer Vision and Pattern Recognition · Computer Science 2021-01-27 Pranjay Shyam , Kuk-Jin Yoon , Kyung-Soo Kim

Low-light and underwater videos suffer from poor visibility, low contrast, and high noise, necessitating enhancements in visual quality. However, existing approaches typically rely on paired ground truth, which limits their practicality and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yini Li , Nantheera Anantrasirichai

One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes. To alleviate this problem, an off-the-shelf image generator can be applied to synthesize additional training…

Computer Vision and Pattern Recognition · Computer Science 2019-11-19 Satoshi Tsutsui , Yanwei Fu , David Crandall

In the context of few-shot classification, the goal is to train a classifier using a limited number of samples while maintaining satisfactory performance. However, traditional metric-based methods exhibit certain limitations in achieving…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Fatemeh Askari , Amirreza Fateh , Mohammad Reza Mohammadi

Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage,…

Computation and Language · Computer Science 2019-04-01 Jingqing Zhang , Piyawat Lertvittayakumjorn , Yike Guo

Object classes that surround us have a natural tendency to emerge at varying levels of abstraction. We propose a Bayesian approach to zero-shot learning (ZSL) that introduces the notion of meta-classes and implements a Bayesian hierarchy…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Sarkhan Badirli , Zeynep Akata , Murat Dundar

Machine unlearning aims to remove the influence of specific samples from a trained model. A key challenge in this process is over-unlearning, where the model's performance on the remaining data significantly drops due to the change in the…

Machine Learning · Computer Science 2025-07-30 Huiqiang Chen , Tianqing Zhu , Xin Yu , Wanlei Zhou

Few-shot segmentation focuses on the generalization of models to segment unseen object instances with limited training samples. Although tremendous improvements have been achieved, existing methods are still constrained by two factors. (1)…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Xianghui Yang , Bairun Wang , Kaige Chen , Xinchi Zhou , Shuai Yi , Wanli Ouyang , Luping Zhou

Part of the appeal of Visual Question Answering (VQA) is its promise to answer new questions about previously unseen images. Most current methods demand training questions that illustrate every possible concept, and will therefore never…

Computer Vision and Pattern Recognition · Computer Science 2016-11-22 Damien Teney , Anton van den Hengel

Embedding inversion, i.e., reconstructing text given its embedding and black-box access to the embedding encoder, is a fundamental problem in both NLP and security. From the NLP perspective, it helps determine how much semantic information…

Computation and Language · Computer Science 2025-04-02 Collin Zhang , John X. Morris , Vitaly Shmatikov

Incorporating a temporal dimension into pretrained image diffusion models for video generation is a prevalent approach. However, this method is computationally demanding and necessitates large-scale video datasets. More critically, the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Dengsheng Chen , Jie Hu , Xiaoming Wei , Enhua Wu

In recent years, deep neural networks for image inhomogeneity reduction have shown promising results. However, current methods with (un)supervised solutions require preparing a training dataset, which is expensive and laborious for data…

Image and Video Processing · Electrical Eng. & Systems 2026-02-16 Hongxu Yang , Edina Timko , Brice Fernandez

Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…

Image and Video Processing · Electrical Eng. & Systems 2021-12-14 Hochang Rhee , Yeong Il Jang , Seyun Kim , Nam Ik Cho