paper-with-me

홈 › Papers

Maximum Manifold Capacity Representations in State Representation Learning

2024-05-22 · Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad

The expanding research on manifold-based self-supervised learning (SSL) builds on the manifold hypothesis, which suggests that the inherent complexity of high-dimensional data can be unraveled through lower-dimensional manifold embeddings. Capitalizing on this, DeepInfomax with an unbalanced atlas (DIM-UA) has emerged as a powerful tool and yielded impressive results for state representations in reinforcement learning. Meanwhile, Maximum Manifold Capacity Representation (MMCR) presents a new frontier for SSL by optimizing class separability via manifold compression. However, MMCR demands extensive input views, resulting in significant computational costs and protracted pre-training durations. Bridging this gap, we present an innovative integration of MMCR into existing SSL methods, incorporating a discerning regularization strategy that enhances the lower bound of mutual information. We also propose a novel state representation learning method extending DIM-UA, embedding a nuclear norm loss to enforce manifold consistency robustly. On experimentation with the Atari Annotated RAM Interface, our method improves DIM-UA significantly with the same number of target encoding dimensions. The mean F1 score averaged over categories is 78% compared to 75% of DIM-UA. There are also compelling gains when implementing SimCLR and Barlow Twins. This supports our SSL innovation as a paradigm shift, enabling more nuanced high-dimensional data representations.

📄 PDF Abstract BibTeX arXiv:2405.13848

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…
Kaiming Initialization 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations

2023-03-06 · NeurIPS 2023 11 · Thomas Yerxa, Yilun Kuang, Eero Simoncelli, SueYeon Chung

The efficient coding hypothesis proposes that the response properties of sensory systems are adapted to the statistics of their inputs such that they capture maximal information about the environment, subject to biologic…

Contrastive LearningObject RecognitionSelf-Supervised Learning

Generalized Category Discovery via Token Manifold Capacity Learning

2025-05-20 · Luyao Tang, Kunze Huang, Chaoqi Chen, Cheng Chen

Generalized category discovery (GCD) is essential for improving deep learning models' robustness in open-world scenarios by clustering unlabeled data containing both known and novel categories. Traditional GCD methods fo…

Clustering

Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations

2024-06-13 · Rylan Schaeffer, Victor Lecomte, Dhruv Bhandarkar Pai, Andres Carranza 외

Maximum Manifold Capacity Representations (MMCR) is a recent multi-view self-supervised learning (MVSSL) method that matches or surpasses other leading MVSSL methods. MMCR is intriguing because it does not fit neatly int…

Self-Supervised Learning

MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis

2026-01-28 · Zeyang Huang, Takanori Fujiwara, Angelos Chatzimparmpas, Wandrille Duchemin 외 arxiv

We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervised learning approach to more efficiently encode low-dimensional manifold …

Self-Supervised LearningDimensionality Reduction

Classification and Geometry of General Perceptual Manifolds

2017-10-17 · SueYeon Chung, Daniel D. Lee, Haim Sompolinsky

Perceptual manifolds arise when a neural population responds to an ensemble of sensory signals associated with different physical features (e.g., orientation, pose, scale, location, and intensity) of the same perceptual …

ClassificationGeneral ClassificationObjectObject Recognition