Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
- URL: http://arxiv.org/abs/2006.00412v1
- Date: Sun, 31 May 2020 02:08:01 GMT
- Title: Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
- Authors: Hantao Yao, Shaobo Min, Yongdong Zhang, Changsheng Xu
- Abstract summary: We propose a novel Attribute-Induced Bias Eliminating (AIBE) module for Transductive ZSL.
For the visual bias between two domains, the Mean-Teacher module is first leveraged to bridge the visual representation discrepancy between two domains.
An attentional graph attribute embedding is proposed to reduce the semantic bias between seen and unseen categories.
Finally, for the semantic-visual bias in the unseen domain, an unseen semantic alignment constraint is designed to align visual and semantic space in an unsupervised manner.
- Score: 144.94728981314717
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Transductive Zero-shot learning (ZSL) targets to recognize the unseen
categories by aligning the visual and semantic information in a joint embedding
space. There exist four kinds of domain biases in Transductive ZSL, i.e.,
visual bias and semantic bias between two domains and two visual-semantic
biases in respective seen and unseen domains, but existing work only focuses on
the part of them, which leads to severe semantic ambiguity during the knowledge
transfer. To solve the above problem, we propose a novel Attribute-Induced Bias
Eliminating (AIBE) module for Transductive ZSL. Specifically, for the visual
bias between two domains, the Mean-Teacher module is first leveraged to bridge
the visual representation discrepancy between two domains with unsupervised
learning and unlabelled images. Then, an attentional graph attribute embedding
is proposed to reduce the semantic bias between seen and unseen categories,
which utilizes the graph operation to capture the semantic relationship between
categories. Besides, to reduce the semantic-visual bias in the seen domain, we
align the visual center of each category, instead of the individual visual data
point, with the corresponding semantic attributes, which further preserves the
semantic relationship in the embedding space. Finally, for the semantic-visual
bias in the unseen domain, an unseen semantic alignment constraint is designed
to align visual and semantic space in an unsupervised manner. The evaluations
on several benchmarks demonstrate the effectiveness of the proposed method,
e.g., obtaining the 82.8%/75.5%, 97.1%/82.5%, and 73.2%/52.1% for
Conventional/Generalized ZSL settings for CUB, AwA2, and SUN datasets,
respectively.
Related papers
- Dual Relation Mining Network for Zero-Shot Learning [48.89161627050706]
We propose a Dual Relation Mining Network (DRMN) to enable effective visual-semantic interactions and learn semantic relationship among attributes for knowledge transfer.
Specifically, we introduce a Dual Attention Block (DAB) for visual-semantic relationship mining, which enriches visual information by multi-level feature fusion.
For semantic relationship modeling, we utilize a Semantic Interaction Transformer (SIT) to enhance the generalization of attribute representations among images.
arXiv Detail & Related papers (2024-05-06T16:31:19Z) - Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided
Relation Alignment and Adaptation [98.51938442785179]
Incremental few-shot semantic segmentation aims to incrementally extend a semantic segmentation model to novel classes.
This task faces a severe semantic-aliasing issue between base and novel classes due to data imbalance.
We propose the Semantic-guided Relation Alignment and Adaptation (SRAA) method that fully considers the guidance of prior semantic information.
arXiv Detail & Related papers (2023-05-18T10:40:52Z) - Progressive Semantic-Visual Mutual Adaption for Generalized Zero-Shot
Learning [74.48337375174297]
Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain.
We deploy the dual semantic-visual transformer module (DSVTM) to progressively model the correspondences between prototypes and visual features.
DSVTM devises an instance-motivated semantic encoder that learns instance-centric prototypes to adapt to different images, enabling the recast of the unmatched semantic-visual pair into the matched one.
arXiv Detail & Related papers (2023-03-27T15:21:43Z) - Cluster-based Contrastive Disentangling for Generalized Zero-Shot
Learning [25.92340532509084]
Generalized Zero-Shot Learning (GZSL) aims to recognize both seen and unseen classes by training only the seen classes.
We propose a Cluster-based Contrastive Disentangling (CCD) method to improve GZSL by alleviating the semantic gap and domain shift problems.
arXiv Detail & Related papers (2022-03-05T02:50:12Z) - Semantics-Guided Contrastive Network for Zero-Shot Object detection [67.61512036994458]
Zero-shot object detection (ZSD) is a new challenge in computer vision.
We develop ContrastZSD, a framework that brings contrastive learning mechanism into the realm of zero-shot detection.
Our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks.
arXiv Detail & Related papers (2021-09-04T03:32:15Z) - 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) - Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning [150.42959029611657]
Domain-aware Visual Bias Eliminating (DVBE) network constructs two complementary visual representations.
For unseen images, we automatically search an optimal semantic-visual alignment architecture.
arXiv Detail & Related papers (2020-03-30T08:17:04Z)
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.