D2S-RSG-SSD:双重采样与随机子样本生成用于自我监督的真实图像去除.
IEEE transactions on pattern analysis and machine intelligence
|February 17, 2026
概括
本研究引入了一种新的自我监督的图像否定框架,即双重采样与随机子样本生成 (D2S-RSG-SSD),以克服当前方法的局限性. 它有效地减少噪音和文物,改善现实世界的图像质量.
科学领域:
- 计算机视觉 计算机视觉
- 图像处理 图像处理
- 机器学习 机器学习
背景情况:
- 自主监督的图像反显示出希望,特别是在盲点网络 (BSN) 中.
- 现有的BSN面临着局限性:不切实际的噪声假设,因中心点掩盖而导致的信息丢失,噪声过度拟合和棋盘工件.
- 这些限制阻碍了在现实世界中复杂的噪音场景中的性能.
研究的目的:
- 开发一种新的自我监督的报销框架,解决当前BSN的局限性.
- 为了在真实世界的图像条件下提高光性能和稳定性.
- 为了减少噪音,减轻信息丢失,并消除采样诱导的工件.
主要方法:
- 引入了双重采样与随机子样本生成 (D2S-RSG-SSD) 框架.
- 采用随机子样本生成 (RSG) 和交叉配对损失 ($\mathcal {L}_{RSG}$) 来打破噪声依赖.
- 使用双双采样 (D2S) 策略,采用双分支架构和固定的采样模式,以减少信息丢失和噪音过度拟合.
- 开发了一个专门的文物清除器来处理棋盘文物,保存图像细节.
主要成果:
- D2S-RSG-SSD框架在基准真实噪声数据集和自我捕获图像上表现出了稳定性和通用性.
- 与现有的自我监督的消毒方法相比,实现了更高的性能.
- 有效地减少噪音,最大限度地减少信息丢失,并纠正没有过度平滑的棋盘工件.
结论:
- 拟议的D2S-RSG-SSD框架在自我监督的图像染方面取得了重大进展.
- 该框架成功地克服了以前方法的关键局限性,在实际场景中实现了有效的拒绝.
- 该方法与各种先进的无线化网络兼容,提供了超越BSN的灵活性.
相关概念视频
Random Sampling Method
15.1K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. Data are the result of sampling from a population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest. Among the various sampling methods used by...
15.1K
Downsampling
714
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
714
Upsampling
649
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
649
Deconvolution
616
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
616
Sampling Methods: Overview
3.5K
A sample refers to a smaller subset representative of a larger population. In analytical chemistry, studying or analyzing an entire population is often impractical or impossible. Therefore, samples are used to draw inferences and generalize the whole population. The sampling method selects individuals or items from a population to create a sample. Standard sampling methods include random, judgemental, systematic, stratified, and cluster sampling.
In analytical chemistry, the choice of...
In analytical chemistry, the choice of...
3.5K
