paper-with-me

Papers

Reverse Engineering Self-Supervised Learning

2023-05-24 · NeurIPS 2023 11 · Ido Ben-Shaul, Ravid Shwartz-Ziv, Tomer Galanti, Shai Dekel, Yann Lecun

Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge. This paper presents an in-depth empirical analysis of SSL-trained representations, encompassing diverse models, architectures, and hyperparameters. Our study reveals an intriguing aspect of the SSL training process: it inherently facilitates the clustering of samples with respect to semantic labels, which is surprisingly driven by the SSL objective's regularization term. This clustering process not only enhances downstream classification but also compresses the data information. Furthermore, we establish that SSL-trained representations align more closely with semantic classes rather than random classes. Remarkably, we show that learned representations align with semantic classes across various hierarchical levels, and this alignment increases during training and when moving deeper into the network. Our findings provide valuable insights into SSL's representation learning mechanisms and their impact on performance across different sets of classes.

📄 PDF Abstract BibTeX arXiv:2305.15614

Code (1)

lightly-ai/lightly 공식 구현 pytorch

Tasks

ClusteringRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Multi-modal Learning for WebAssembly Reverse Engineering

2024-04-04 · Hanxian Huang, Jishen Zhao

The increasing adoption of WebAssembly (Wasm) for performance-critical and security-sensitive tasks drives the demand for WebAssembly program comprehension and reverse engineering. Recent studies have introduced machine …

Language ModellingSelf-Supervised Learning

Towards Reverse-Engineering the Brain: Brain-Derived Neuromorphic Computing Approach with Photonic, Electronic, and Ionic Dynamicity in 3D integrated circuits

2024-03-28 · S. J. Ben Yoo, Luis El-Srouji, Suman Datta, Shimeng Yu 외

The human brain has immense learning capabilities at extreme energy efficiencies and scale that no artificial system has been able to match. For decades, reverse engineering the brain has been one of the top priorities o…

Self-LearningSelf-Supervised Learning

Self-supervised Learning to Bring Dual Reversed Rolling Shutter Images Alive

2023-05-31 · ICCV 2023 1 · Wei Shang, Dongwei Ren, Chaoyu Feng, Xiaotao Wang 외

Modern consumer cameras usually employ the rolling shutter (RS) mechanism, where images are captured by scanning scenes row-by-row, yielding RS distortions for dynamic scenes. To correct RS distortions, existing methods …

Self-Supervised Learning

From Density to Geometry: YOLOv8 Instance Segmentation for Reverse Engineering of Optimized Structures

2024-04-29 · Thomas Rochefort-Beaudoin, Aurelian Vadean, Sofiane Achiche, Niels Aage

This paper introduces YOLOv8-TO, a novel approach for reverse engineering of topology-optimized structures into interpretable geometric parameters using the YOLOv8 instance segmentation model. Density-based topology opti…

Instance Segmentation

A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection

2022-02-25 · Wenrui Zhang, Shijia Geng, Shenda Hong

Learning representations from electrocardiogram (ECG) signals can serve as a fundamental step for different machine learning-based ECG tasks. In order to extract general ECG representations that can be adapted to various…

Representation LearningSelf-Supervised Learning