English
Related papers

Related papers: An Integral Projection-based Semantic Autoencoder …

200 papers

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a…

Human-Computer Interaction · Computer Science 2021-08-17 Shichao Jia , Zeyu Li , Nuo Chen , Jiawan Zhang

This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…

Computer Vision and Pattern Recognition · Computer Science 2016-07-28 Maxime Bucher , Stéphane Herbin , Frédéric Jurie

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, many recent works…

Computer Vision and Pattern Recognition · Computer Science 2021-05-26 Shiqi Yang , Kai Wang , Luis Herranz , Joost van de Weijer

Audio-visual generalized zero-shot learning is a rapidly advancing domain that seeks to understand the intricate relations between audio and visual cues within videos. The overarching goal is to leverage insights from seen classes to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Shentong Mo , Pedro Morgado

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions. Some recent papers have shown the importance of localized features together with fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2021-03-10 Shiqi Yang , Kai Wang , Luis Herranz , Joost van de Weijer

Wireless goal-oriented semantic communication (GSC) has emerged as a promising paradigm by directly optimizing task performance. However, existing GSC frameworks typically operate on entire images and rely on labeled data for classification…

Image and Video Processing · Electrical Eng. & Systems 2026-04-14 Zhitong Ni , Yansha Deng , Jinhong Yuan

Zero shot learning -- the problem of training and testing on a completely disjoint set of classes -- relies greatly on its ability to transfer knowledge from train classes to test classes. Traditionally semantic embeddings consisting of…

Computation and Language · Computer Science 2020-12-14 Abhinaba Roy , Deepanway Ghosal , Erik Cambria , Navonil Majumder , Rada Mihalcea , Soujanya Poria

Many recent methods of zero-shot learning (ZSL) attempt to utilize generative model to generate the unseen visual samples from semantic descriptions and random noise. Therefore, the ZSL problem becomes a traditional supervised…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Shibing Xu , Zishu Gao , Guojun Xie

Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are…

Computer Vision and Pattern Recognition · Computer Science 2018-01-30 Ashish Mishra , M Shiva Krishna Reddy , Anurag Mittal , Hema A Murthy

The goal of Open-Vocabulary Compositional Zero-Shot Learning (OV-CZSL) is to recognize attribute-object compositions in the open-vocabulary setting, where compositions of both seen and unseen attributes and objects are evaluated. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Yihang Duan , Jiong Wang , Pengpeng Zeng , Ji Zhang , Lei Zhao , Chong Wang , Jingkuan Song , Lianli Gao

Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class…

Computer Vision and Pattern Recognition · Computer Science 2021-02-04 Lu Liu , Tianyi Zhou , Guodong Long , Jing Jiang , Xuanyi Dong , Chengqi Zhang

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which…

Computer Vision and Pattern Recognition · Computer Science 2016-05-31 Soravit Changpinyo , Wei-Lun Chao , Boqing Gong , Fei Sha

Zero-shot Semantic Segmentation (ZSS) aims to segment categories that are not annotated during training. While fine-tuning vision-language models has achieved promising results, these models often overfit to seen categories due to the lack…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Jialei Chen , Xu Zheng , Dongyue Li , Chong Yi , Seigo Ito , Danda Pani Paudel , Luc Van Gool , Hiroshi Murase , Daisuke Deguchi

Generalized Zero-shot Semantic Segmentation aims to segment both seen and unseen categories only under the supervision of the seen ones. To tackle this, existing methods adopt the large-scale Vision Language Models (VLMs) which obtain…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Jialei Chen , Daisuke Deguchi , Chenkai Zhang , Xu Zheng , Hiroshi Murase

Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable.…

Computer Vision and Pattern Recognition · Computer Science 2017-05-05 Yang Long , Li Liu , Ling Shao , Fumin Shen , Guiguang Ding , Jungong Han

Deep learning models are increasingly deployed on edge Internet of Things (IoT) devices. However, these models typically operate under supervised conditions and fail to recognize unseen classes different from training. To address this,…

Artificial Intelligence · Computer Science 2024-07-30 Dinghao Xue , Xiaoran Fan , Tao Chen , Guohao Lan , Qun Song

This paper studies the problem of generalized zero-shot learning which requires the model to train on image-label pairs from some seen classes and test on the task of classifying new images from both seen and unseen classes. Most previous…

Computer Vision and Pattern Recognition · Computer Science 2019-05-28 He Huang , Changhu Wang , Philip S. Yu , Chang-Dong Wang

Zero-shot recognition (ZSR) aims to recognize target-domain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative…

Computer Vision and Pattern Recognition · Computer Science 2016-12-06 Ziming Zhang , Venkatesh Saligrama