Translational Concept Embedding for Generalized Compositional Zero-shot Learning
Not on the map. Why?
Abstract (arXiv)
Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts. This task is very challenging because of not only the gap between seen and unseen concepts but also the contextual dependency between attributes and objects. This paper introduces a new approach, termed translational concept embedding, to solve these two difficulties in a unified framework. It models the effect of applying an attribute to an object as adding a translational attribute feature to an object prototype. We explicitly take into account of the contextual dependency between attributes and objects by generating translational attribute features conditionally dependent on the object prototypes. Furthermore, we design a ratio variance constraint loss to promote the model's generalization ability on unseen concepts. It regularizes the distances between concepts by utilizing knowledge from their pretrained word embeddings. We evaluate the performance of our model under both the unbiased and biased concept classification tasks, and show that our model is able to achieve good balance in predicting unseen and seen concepts.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 20 Dec 2021.
Builds on
22 of 33 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
- 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
- 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
- 2021Open World Compositional Zero-Shot Learningcited by 100
10 more
- 2020Symmetry and Group in Attribute-Object Compositionscited by 89
- 2020A causal view of compositional zero-shot recognitioncited by 78
- 2016Boosting Image Captioning with Attributescited by 76
- 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
- 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
- 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
- 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
- 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
- 2020Multi-label Zero-shot Classification by Learning to Transfer from External Knowledgecited by 6
- 2020Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Scorecited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.