Semantic Borrowing for Generalized Zero-Shot Learning

• URL: http://arxiv.org/abs/2102.04969v1
• Date: Sat, 30 Jan 2021 12:14:28 GMT
• Title: Semantic Borrowing for Generalized Zero-Shot Learning
• Authors: Xiao-wei Chen (Sun Yat-sen University)
• Abstract summary: Generalized zero-shot learning (GZSL) is one of the most realistic problems, but also one of the most challenging. Instance-borrowing methods and methods solve this problem to some extent with the help of testing semantics. A novel method called Semantic Borrowing for improving GZSL methods with compatibility metric learning under CIII is proposed in this paper.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalized zero-shot learning (GZSL) is one of the most realistic problems, but also one of the most challenging problems due to the partiality of the classifier to supervised classes. Instance-borrowing methods and synthesizing methods solve this problem to some extent with the help of testing semantics, but therefore neither can be used under the class-inductive instance-inductive (CIII) training setting where testing data are not available, and the latter require the training process of a classifier after generating examples. In contrast, a novel method called Semantic Borrowing for improving GZSL methods with compatibility metric learning under CIII is proposed in this paper. It borrows similar semantics in the training set, so that the classifier can model the relationship between the semantics of zero-shot and supervised classes more accurately during training. In practice, the information of semantics of unseen or unknown classes would not be available for training while this approach does NOT need any information of semantics of unseen or unknown classes. The experimental results on representative GZSL benchmark datasets show that it can reduce the partiality of the classifier to supervised classes and improve the performance of generalized zero-shot classification.

Related papers

• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Learning Context-aware Classifier for Semantic Segmentation [88.88198210948426]
  In this paper, contextual hints are exploited via learning a context-aware classifier. Our method is model-agnostic and can be easily applied to generic segmentation models. With only negligible additional parameters and +2% inference time, decent performance gain has been achieved on both small and large models.
  arXiv  Detail & Related papers  (2023-03-21T07:00:35Z)
• Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation [40.09476732999614]
  Mask proposal models have significantly improved the performance of zero-shot semantic segmentation. The use of a background' embedding during training in these methods is problematic as the resulting model tends to over-learn and assign all unseen classes as the background class instead of their correct labels. This paper proposes novel class enhancement losses to bypass the use of the background embbedding during training, and simultaneously exploit the semantic relationship between text embeddings and mask proposals by ranking the similarity scores.
  arXiv  Detail & Related papers  (2023-01-18T06:55:02Z)
• Progressive Class Semantic Matching for Semi-supervised Text Classification [26.794533973357403]
  We investigate the marriage between semi-supervised learning and a pre-trained language model. By means of extensive experiments, we show that our method can bring remarkable improvement to baselines.
  arXiv  Detail & Related papers  (2022-05-20T13:59:03Z)
• Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation [25.070027668717422]
  Generalized zero-shot semantic segmentation (GZS3) predicts pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a generative approach that synthesizes visual features of unseen classes from corresponding semantic ones. We propose a discriminative approach to address limitations in a unified framework.
  arXiv  Detail & Related papers  (2021-08-14T13:33:58Z)
• CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition [52.66360172784038]
  We propose a clustering-based model, which considers all training samples at once, instead of optimizing for each instance individually. We call the proposed method CLASTER and observe that it consistently improves over the state-of-the-art in all standard datasets.
  arXiv  Detail & Related papers  (2021-01-18T12:46:24Z)
• Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning [49.04790688256481]
  The goal of generalized zero-shot learning (GZSL) is to recognise both seen and unseen classes. Most GZSL methods typically learn to synthesise visual representations from semantic information on the unseen classes. We propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features.
  arXiv  Detail & Related papers  (2021-01-09T05:21:27Z)
• Generalized Zero-Shot Learning Via Over-Complete Distribution [79.5140590952889]
  We propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. The effectiveness of the framework is evaluated using both Zero-Shot Learning and Generalized Zero-Shot Learning protocols.
  arXiv  Detail & Related papers  (2020-04-01T19:05:28Z)
• Domain segmentation and adjustment for generalized zero-shot learning [22.933463036413624]
  In zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes. We argue that synthesizing unseen data may not be an ideal approach for addressing the domain shift caused by the imbalance of the training data. In this paper, we propose to realize the generalized zero-shot recognition in different domains.
  arXiv  Detail & Related papers  (2020-02-01T15:00:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.