English
Related papers

Related papers: Cross-Modal Few-Shot Learning: a Generative Transf…

200 papers

Few-shot learning aims to train a classifier that can generalize well when just a small number of labeled examples per class are given. We introduce a transductive maximum margin classifier for few-shot learning (FS-TMMC). The basic idea of…

Computer Vision and Pattern Recognition · Computer Science 2021-10-29 Fei Pan , Chunlei Xu , Jie Guo , Yanwen Guo

Few-Shot Learning (FSL) requires vision models to quickly adapt to brand-new classification tasks with a shift in task distribution. Understanding the difficulties posed by this task distribution shift is central to FSL. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Xu Luo , Jing Xu , Zenglin Xu

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Chengjia Jiang , Tao Wang , Sien Li , Jinyang Wang , Shirui Wang , Antonios Antoniou

Learning novel concepts, remembering previous knowledge, and adapting it to future tasks occur simultaneously throughout a human's lifetime. To model such comprehensive abilities, continual zero-shot learning (CZSL) has recently been…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Wenxuan Zhang , Paul Janson , Kai Yi , Ivan Skorokhodov , Mohamed Elhoseiny

Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples. The unseen classes and low-data problem make few-shot classification very challenging. Many existing approaches extracted…

Computer Vision and Pattern Recognition · Computer Science 2019-10-18 Ruibing Hou , Hong Chang , Bingpeng Ma , Shiguang Shan , Xilin Chen

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…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Ziming Liu , Jingcai Guo , Xiaocheng Lu , Song Guo , Peiran Dong , Jiewei Zhang

We propose generative multitask learning (GMTL), a simple and scalable approach to causal representation learning for multitask learning. Our approach makes a minor change to the conventional multitask inference objective, and improves…

Machine Learning · Computer Science 2022-10-25 Taro Makino , Krzysztof J. Geras , Kyunghyun Cho

Few-shot learning (FSL) presents a challenging learning problem in which only a few samples are available for each class. Decision interpretation is more important in few-shot classification due to a greater chance of error compared to…

Machine Learning · Computer Science 2025-04-01 Mohammad Reza Zarei , Majid Komeili

Zero-shot learning is a new paradigm to classify objects from classes that are not available at training time. Zero-shot learning (ZSL) methods have attracted considerable attention in recent years because of their ability to classify…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Chandan Gautam , Sethupathy Parameswaran , Ashish Mishra , Suresh Sundaram

We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection, which are complementary to each other by definition. Most of the previous works on…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Guangxing Han , Long Chen , Jiawei Ma , Shiyuan Huang , Rama Chellappa , Shih-Fu Chang

Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and crossdomain challenges. In order to alleviate…

Computer Vision and Pattern Recognition · Computer Science 2021-01-26 Cheng Xie , Hongxin Xiang , Ting Zeng , Yun Yang , Beibei Yu , Qing Liu

Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiacong Liu , Shu Luo , Yikai Qin , Yaze Zhao , Yongwei Jiang , Yixiong Zou

In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes,…

Computer Vision and Pattern Recognition · Computer Science 2018-08-03 Rafael Felix , B. G. Vijay Kumar , Ian Reid , Gustavo Carneiro

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

Computation and Language · Computer Science 2024-12-16 Guanghua Hou , Shuhui Cao , Deqiang Ouyang , Ning Wang

Few-shot learning aims to recognize novel classes with few examples. Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Baoquan Zhang , Xutao Li , Yunming Ye , Shanshan Feng

Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scenarios. To overcome these large differences, recent works…

Machine Learning · Computer Science 2022-10-13 Jaehoon Oh , Sungnyun Kim , Namgyu Ho , Jin-Hwa Kim , Hwanjun Song , Se-Young Yun

The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the training on the source domain, which results in lacking…

Computer Vision and Pattern Recognition · Computer Science 2021-09-06 Xiyao Liu , Zhong Ji , Yanwei Pang , Zhongfei Zhang

In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge. It is mainly caused by the characteristic of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Xusheng Cao , Haori Lu , Linlan Huang , Xialei Liu , Ming-Ming Cheng

Transductive Few-Shot Learning (TFSL) has recently attracted increasing attention since it typically outperforms its inductive peer by leveraging statistics of query samples. However, previous TFSL methods usually encode uniform prior that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Long Tian , Jingyi Feng , Wenchao Chen , Xiaoqiang Chai , Liming Wang , Xiyang Liu , Bo Chen

Recognizing multiple labels of an image is a practical yet challenging task, and remarkable progress has been achieved by searching for semantic regions and exploiting label dependencies. However, current works utilize RNN/LSTM to…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Tianshui Chen , Liang Lin , Riquan Chen , Xiaolu Hui , Hefeng Wu