paper-with-me

Papers

MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations

2024-06-18 · Reza Akbarian Bafghi, Nidhin Harilal, Claire Monteleoni, Maziar Raissi

This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable Diffusion to replace an augmented instance of a real image, facilitating the learning of cross real-synthetic image representations. Our key insight is that while models trained solely on synthetic images underperform, combining real and synthetic data leads to more robust and adaptable representations. Experiments show MixDiff enhances SimCLR, BarlowTwins, and DINO across various robustness datasets and domain transfer tasks, boosting SimCLR's ImageNet-1K accuracy by 4.56%. Our framework also demonstrates comparable performance without needing any augmentations, a surprising finding in SSL where augmentations are typically crucial.

📄 PDF Abstract BibTeX arXiv:2406.12368

Code (1)

cryptonymous9/mixing-ssl 공식 구현 pytorch

Tasks

Image ClassificationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Average Pooling 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…

Similar Papers 제목 키워드 기반

Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments

2024-08-19 · Heeyoung Lee, Hoyoon Byun, Changdae Oh, JinYeong Bak 외

Accessing machine learning models through remote APIs has been gaining prevalence following the recent trend of scaling up model parameters for increased performance. Even though these models exhibit remarkable ability, …

Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement

2021-02-01 · Zhenqi Fu, Xueyang Fu, Yue Huang, Xinghao Ding

To improve the quality of underwater images, various kinds of underwater image enhancement (UIE) operators have been proposed during the past few years. However, the lack of effective objective evaluation methods limits …

Image EnhancementUIE

A Simple Data Mixing Prior for Improving Self-Supervised Learning

2022-06-15 · CVPR 2022 1 · Sucheng Ren, Huiyu Wang, Zhengqi Gao, Shengfeng He 외

Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images …

Representation LearningSelf-Supervised Learning

Dynamical spectral unmixing of multitemporal hyperspectral images

2015-10-14 · Simon Henrot, Jocelyn Chanussot, Christian Jutten

In this paper, we consider the problem of unmixing a time series of hyperspectral images. We propose a dynamical model based on linear mixing processes at each time instant. The spectral signatures and fractional abundan…

Time SeriesTime Series Analysis

Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization

2021-09-30 · Hannah M. Schlüter, Jeremy Tan, Benjamin Hou, Bernhard Kainz

We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies (NSA), for training an end-to-end model for anomaly detection and localization using only normal training data. NSA integrates Poisso…

Anomaly ClassificationAnomaly DetectionAnomaly SegmentationData Augmentation+3