Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning

11/19/2022
by   Chenyi Jiang, et al.
0

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions from seen states and objects. The disparity between the manually labeled semantic information and its actual visual features causes a significant imbalance of visual deviation in the distribution of various object classes and state classes, which is ignored by existing methods. To ameliorate these issues, we consider the CZSL task as an unbalanced multi-label classification task and propose a novel method called MUtual balancing in STate-object components (MUST) for CZSL, which provides a balancing inductive bias for the model. In particular, we split the classification of the composition classes into two consecutive processes to analyze the entanglement of the two components to get additional knowledge in advance, which reflects the degree of visual deviation between the two components. We use the knowledge gained to modify the model's training process in order to generate more distinct class borders for classes with significant visual deviations. Extensive experiments demonstrate that our approach significantly outperforms the state-of-the-art on MIT-States, UT-Zappos, and C-GQA when combined with the basic CZSL frameworks, and it can improve various CZSL frameworks. Our codes are available on https://anonymous.4open.science/r/MUST_CGE/.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/20/2022

Learning Attention Propagation for Compositional Zero-Shot Learning

Compositional zero-shot learning aims to recognize unseen compositions o...
research
06/29/2022

Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen composi...
research
11/29/2021

3D Compositional Zero-shot Learning with DeCompositional Consensus

Parts represent a basic unit of geometric and semantic similarity across...
research
11/19/2022

Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts...
research
08/08/2023

Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning

Compositional zero-shot learning (CZSL) aims to recognize unseen composi...
research
09/02/2023

GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning

This paper investigates a challenging problem of zero-shot learning in t...
research
01/29/2021

Open World Compositional Zero-Shot Learning

Compositional Zero-Shot learning (CZSL) requires to recognize state-obje...

Please sign up or login with your details

Forgot password? Click here to reset