paper-with-me

Papers

An Empirical Study on Disentanglement of Negative-free Contrastive Learning

2022-06-09 · Jinkun Cao, Ruiqian Nai, Qing Yang, Jialei Huang, Yang Gao

Negative-free contrastive learning methods have attracted a lot of attention with simplicity and impressive performances for large-scale pretraining. However, its disentanglement property remains unexplored. In this paper, we examine negative-free contrastive learning methods to study the disentanglement property empirically. We find that existing disentanglement metrics fail to make meaningful measurements for high-dimensional representation models, so we propose a new disentanglement metric based on Mutual Information between latent representations and data factors. With this proposed metric, we benchmark the disentanglement property of negative-free contrastive learning on both popular synthetic datasets and a real-world dataset CelebA. Our study shows that the investigated methods can learn a well-disentangled subset of representation. As far as we know, we are the first to extend the study of disentangled representation learning to high-dimensional representation space and introduce negative-free contrastive learning methods into this area. The source code of this paper is available at \url{https://github.com/noahcao/disentanglement_lib_med}.

📄 PDF Abstract BibTeX arXiv:2206.04756

Code (1)

noahcao/disentanglement_lib_med 공식 구현 tf

Tasks

Contrastive LearningDisentanglementRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning

2022-03-15 · Xiang Chen, Zhentao Fan, Pengpeng Li, Longgang Dai 외

We offer a practical unpaired learning based image dehazing network from an unpaired set of clear and hazy images. This paper provides a new perspective to treat image dehazing as a two-class separated factor disentangle…

Contrastive LearningDisentanglementImage DehazingImage Reconstruction+1

Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation

2023-05-25 · Ilan Naiman, Nimrod Berman, Omri Azencot

Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, where data is time-dependent. However, the…

DisentanglementRepresentation LearningTime Series

Contrastive Speaker Embedding With Sequential Disentanglement

2023-09-23 · Youzhi Tu, Man-Wai Mak, Jen-Tzung Chien

Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption is incorrect because speech signals cont…

Contrastive LearningDisentanglement

Non-negative Contrastive Learning

2024-03-19 · Yifei Wang, Qi Zhang, Yaoyu Guo, Yisen Wang

Deep representations have shown promising performance when transferred to downstream tasks in a black-box manner. Yet, their inherent lack of interpretability remains a significant challenge, as these features are often …

Contrastive LearningDisentanglementfeature selection

$\mathrm{ECI}_{\mathrm{sem}}$: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives

2026-03-22 · Aarush Sinha, Rahul Seetharaman, Aman Bansal arxiv

Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose $\mathrm{ECI}_{\mathrm{sem}}$, a semantic residual variant of Effective Contrastive Infor…