Self-supervised learning disentangled group representation as feature

Self-supervised learning disentangled group representation as feature

A good visual representation is an inference map from observations (images) to features (vectors) that faithfully reflects the hidden modularized generative factors (semantics). In this paper, we formulate the notion of “good” representation from a group-theoretic view using Higgins’ definition of d...

Saved in:

書目詳細資料
Main Authors:	WANG, Tan, YUE, Zhongqi, HUANG, Jianqiang, SUN, Qianru, ZHANG, Hanwang
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2021
主題:	Databases and Information Systems Graphics and Human Computer Interfaces
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/6227 https://ink.library.smu.edu.sg/context/sis_research/article/7230/viewcontent/NIPS2021_Causal_SSL_final.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Singapore Management University
語言:	English

相似書籍

Visual commonsense representation learning via causal inference
由: WANG, Tan, et al.
出版: (2020)

Unbiased multiple instance learning for weakly supervised video anomaly detection
由: LYU, Hui, et al.
出版: (2023)

Exploring diffusion time-steps for unsupervised representation learning
由: YUE, Zhongqi, et al.
出版: (2024)

Joint representation learning of cross-lingual words and entities via attentive distant supervision
由: CAO, Yixin, et al.
出版: (2018)

Transporting causal mechanisms for unsupervised domain adaptation
由: YUE, Zhongqi, et al.
出版: (2021)

Few-shot learner parameterization by diffusion time-steps
由: YUE, Zhongqi, et al.
出版: (2024)

Semantic scene completion with cleaner self
由: WANG, Fengyun, et al.
出版: (2023)

Learning to teach and learn for semi-supervised few-shot image classification
由: LI, Xinzhe, et al.
出版: (2021)

Disentangling multi-view representations beyond inductive bias
由: KE, Guanzhou, et al.
出版: (2023)

Self-regulation for semantic segmentation
由: ZHANG, Dong, et al.
出版: (2021)

Semi-supervised domain adaptation with subspace learning for visual recognition
由: YAO, Ting, et al.
出版: (2015)

Visual Commonsense R-CNN
由: WANG, Tan, et al.
出版: (2020)

A theory-driven self-labeling refinement method for contrastive representation learning
由: ZHOU, Pan, et al.
出版: (2021)

Learning comprehensive global features in person re-identification: Ensuring discriminativeness of more local regions
由: XIA, Jiali, et al.
出版: (2023)

Extracting class activation maps from non-discriminative features as well
由: CHEN, Zhaozheng, et al.
出版: (2023)

Compositional prompt tuning with motion cues for open-vocabulary video relation detection
由: GAO, Kaifeng, et al.
出版: (2023)

Class-incremental exemplar compression for class-incremental learning
由: LUO, Zilin, et al.
出版: (2023)

Prototypical contrastive learning of unsupervised representations
由: LI, Junnan, et al.
出版: (2021)

Mnemonics training: Multi-class incremental learning without forgetting
由: LIU, Yaoyao, et al.
出版: (2020)

Causal attention for unbiased visual recognition
由: WANG, Tan, et al.
出版: (2021)

Revisiting disentanglement and fusion on modality and context in conversational multimodal emotion recognition
由: LI, Bobo, et al.
出版: (2023)

Semi-supervised hierarchical clustering for personalized web image organization
由: MENG, Lei, et al.
出版: (2012)

Class re-activation maps for weakly-supervised semantic segmentation
由: CHEN, Zhaozheng, et al.
出版: (2022)

A Bayesian approach integrating regional and global features for image semantic learning
由: NGUYEN, Luong-Dong, et al.
出版: (2009)

Interactive contrastive learning for self-supervised entity alignment
由: ZENG, Kaisheng, et al.
出版: (2022)

Rethinking multi-view representation learning via distilled disentangling
由: KE, Guanzhou, et al.
出版: (2024)

Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model
由: LI, Chengjiang, et al.
出版: (2019)

MMEKG: Multi-modal Event Knowledge Graph towards universal representation across modalities
由: MA, Yubo, et al.
出版: (2022)

Improving Disentangled Representation Learning for Gait Recognition using Group Supervision
由: Lingxiang Yao, et al.
出版: (2022)

Improving Disentangled Representation Learning for Gait Recognition using Group Supervision
由: Yao L.
出版: (2023)

Deconfounded visual grounding
由: HUANG, Jianqiang, et al.
出版: (2022)

Freestyle layout-to-image synthesis
由: XUE, Han, et al.
出版: (2023)

A simple data mixing prior for improving self-supervised learning
由: REN, Sucheng, et al.
出版: (2022)

Self-supervised multi-class pre-training for unsupervised anomaly detection and segmentation in medical images
由: TIAN, Yu, et al.
出版: (2021)

Self-promoted supervision for few-shot transformer
由: DONG, Bowen, et al.
出版: (2022)

Bridge text and knowledge by learning multi-prototype entity mention embedding
由: CAO, Yixin, et al.
出版: (2017)

VIREO/DVMM at TRECVID 2009: High-level feature extraction, automatic video search, and content-based copy detection
由: NGO, Chong-wah, et al.
出版: (2009)

GANmut: learning interpretable conditional space for a gamut of emotions
由: D'APOLITO, S., et al.
出版: (2021)

Are missing links predictable? An inferential benchmark for knowledge graph completion
由: CAO, Yixin, et al.
出版: (2021)

Log-euclidean metric learning on symmetric positive definite manifold with application to image set classification
由: HUANG, Zhiwu, et al.
出版: (2015)