Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification

2016-07-27 · Maxime Bucher, Stéphane Herbin, Frédéric Jurie

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 metric learning problem. The optimized empirical criterion associates two types of sub-task constraints: metric discriminating capacity and accurate attribute prediction. This results in a novel expression of zero-shot learning not requiring the notion of class in the training phase: only pairs of image/attributes, augmented with a consistency indicator, are given as ground truth. At test time, the learned model can predict the consistency of a test image with a given set of attributes , allowing flexible ways to produce recognition inferences. Despite its simplicity, the proposed approach gives state-of-the-art results on four challenging datasets used for zero-shot recognition evaluation.

📄 PDF Abstract BibTeX arXiv:1607.08085

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeGeneral Classification image-classification Image Classification Metric Learningzero-shot-classificationZero-Shot Image Classification Zero-Shot Learning

Global Semantic Consistency for Zero-Shot Learning

2018-06-22 · Fan Wu, Kai Tian, Jihong Guan, Shuigeng Zhou

In image recognition, there are many cases where training samples cannot cover all target classes. Zero-shot learning (ZSL) utilizes the class semantic information to classify samples of the unseen categories that have n…

Attribute Generalized Zero-Shot Learning Novelty Detection Zero-Shot Learning

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

2020-03-17 · ECCV 2020 8 · Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek 외

Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art …

Action Classification Classification Decoder General Classification+3

Generative Dual Adversarial Network for Generalized Zero-shot Learning

2018-11-12 · CVPR 2019 6 · He Huang, Changhu Wang, Philip S. Yu, Chang-Dong Wang

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 clas…

Generalized Zero-Shot Learning Metric Learning Zero-Shot Learning

RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation

2025-05-21 · Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami

Mapping and understanding complex 3D environments is fundamental to how autonomous systems perceive and interact with the physical world, requiring both precise geometric reconstruction and rich semantic comprehension. W…

GPU Natural Language Queries Object object-detection+3

$S^3$: Synonymous Semantic Space for Improving Zero-Shot Generalization of Vision-Language Models

2024-12-06 · Xiaojie Yin, Qilong Wang, Bing Cao, QinGhua Hu

Recently, many studies have been conducted to enhance the zero-shot generalization ability of vision-language models (e.g., CLIP) by addressing the semantic misalignment between image and text embeddings in downstream ta…

zero-shot-classification Zero-shot Generalization Zero-Shot Learning