Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency regularization restricts the propagation of labeling information due to the exclusion of samples with unconfident pseudo-labels in the model updates. Then, we propose contrastive regularization to improve both efficiency and accuracy of the consistency regularization by well-clustered features of unlabeled data. In specific, after strongly augmented samples are assigned to clusters by their pseudo-labels, our contrastive regularization updates the model so that the features with confident pseudo-labels aggregate the features in the same cluster, while pushing away features in different clusters. As a result, the information of confident pseudo-labels can be effectively propagated into more unlabeled samples during training by the well-clustered features. On benchmarks of semi-supervised learning tasks, our contrastive regularization improves the previous consistency-based methods and achieves state-of-the-art results, especially with fewer training iterations. Our method also shows robust performance on open-set semi-supervised learning where unlabeled data includes out-of-distribution samples.

In part 1, I introduced how we can reason from graphs, why they're so useful, metrics for analyzing and condensing large information, and more. In part 2, I took a look at the CryptoPunks trading network to introduce a higher level of reasoning of graphs -- random worlds and diffusion models. I then took a little bit of a tangent to discuss how we can use Network and Graph Analysis to look at NBA games. This part will use concepts introduced in that story to further my analysis of Graph Machine Learning. I highly recommend reviewing these previous parts before diving into this one as they set this one up well, and many concepts I won't dive into here are already discussed and shown in each of those.

Most conventional crowd counting methods utilize a fully-supervised learning framework to learn a mapping between scene images and crowd density maps. Under the circumstances of such fully-supervised training settings, a large quantity of expensive and time-consuming pixel-level annotations are required to generate density maps as the supervision. One way to reduce costly labeling is to exploit self-structural information and inner-relations among unlabeled images. Unlike the previous methods utilizing these relations and structural information from the original image level, we explore such self-relations from the latent feature spaces because it can extract more abundant relations and structural information. Specifically, we propose S$^2$FPR which can extract structural information and learn partial orders of coarse-to-fine pyramid features in the latent space for better crowd counting with massive unlabeled images. In addition, we collect a new unlabeled crowd counting dataset (FUDAN-UCC) with 4,000 images in total for training. One by-product is that our proposed S$^2$FPR method can leverage numerous partial orders in the latent space among unlabeled images to strengthen the model representation capability and reduce the estimation errors for the crowd counting task. Extensive experiments on four benchmark datasets, i.e. the UCF-QNRF, the ShanghaiTech PartA and PartB, and the UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The source code and dataset are available at https://github.com/bridgeqiqi/S2FPR.

Create a GAN capable of generating high resolution images using TensorFlow 2.0 · Distribute training on a TPU or multiple GPUS · Implement the R2 This course covers the fundamentals necessary for a state-of-the-art GAN. Anyone who experimented with GANs on their own knows that it's easy to throw together a GAN that spits out MNIST digits, but it's another level of difficulty entirely to produce photorealistic images at a resolution higher than a thumbnail. You'll create and train a GAN that can be used in real-world applications. And because training high-resolution networks of any kind is computationally expensively, you'll also learn how to distribute your training across multiple GPUs or TPUs. This allows students to train generators up to 512x512 resolution with no hardware costs at all.

Thus the final output of each single network is 1024 dimensional feature space f(). The distance between query image patch and the tracked patch is small and the distance between query patch and other random patches is encouraged to be larger.

In this article, we aim to provide a general and complete understanding of semi-supervised (SS) causal inference for treatment effects. Specifically, we consider two such estimands: (a) the average treatment effect and (b) the quantile treatment effect, as prototype cases, in an SS setting, characterized by two available data sets: (i) a labeled data set of size $n$, providing observations for a response and a set of high dimensional covariates, as well as a binary treatment indicator; and (ii) an unlabeled data set of size $N$, much larger than $n$, but without the response observed. Using these two data sets, we develop a family of SS estimators which are ensured to be: (1) more robust and (2) more efficient than their supervised counterparts based on the labeled data set only. Beyond the 'standard' double robustness results (in terms of consistency) that can be achieved by supervised methods as well, we further establish root-n consistency and asymptotic normality of our SS estimators whenever the propensity score in the model is correctly specified, without requiring specific forms of the nuisance functions involved. Such an improvement of robustness arises from the use of the massive unlabeled data, so it is generally not attainable in a purely supervised setting. In addition, our estimators are shown to be semi-parametrically efficient as long as all the nuisance functions are correctly specified. Moreover, as an illustration of the nuisance estimators, we consider inverse-probability-weighting type kernel smoothing estimators involving unknown covariate transformation mechanisms, and establish in high dimensional scenarios novel results on their uniform convergence rates, which should be of independent interest. Numerical results on both simulated and real data validate the advantage of our methods over their supervised counterparts with respect to both robustness and efficiency.

When we use labeled data to train a machine-learning algorithm (e.g. When we use unlabeled data to train a machine-learning algorithm and allow it to find patterns in the data(e.g. Using dimensionality reduction to transform raw data into numerical features that can be processed with machine learning that contain information about the original data (e.g. An unsupervised learning task where the algorithm learns patterns in input data to generate new examples (fake data) that would appear to have been drawn from the original dataset. The part of the GAN that generates fake data.

In this paper, we tackle the inductive semi-supervised learning problem that aims to obtain label predictions for out-of-sample data. The proposed approach, called Optimal Transport Induction (OTI), extends efficiently an optimal transport based transductive algorithm (OTP) to inductive tasks for both binary and multi-class settings. A series of experiments are conducted on several datasets in order to compare the proposed approach with state-of-the-art methods. Experiments demonstrate the effectiveness of our approach. We make our code publicly available.

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a label. However, the imperfect ASR result makes unsupervised learning difficult to consistently improve recognition performance especially in the case that multiple powerful teacher models are unavailable. In contrast to conventional unsupervised learning approaches, we adopt the \emph{multi-task learning} (MTL) framework where the $n$-th best ASR hypothesis is used as the label of each task. The seq2seq network is updated through the MTL framework so as to find the common representation that can cover multiple hypotheses. By doing so, the effect of the \emph{hard-decision} errors can be alleviated. We first demonstrate the effectiveness of our self-learning methods through ASR experiments in an accent adaptation task between the US and British English speech. Our experiment results show that our method can reduce the WER on the British speech data from 14.55\% to 10.36\% compared to the baseline model trained with the US English data only. Moreover, we investigate the effect of our proposed methods in a federated learning scenario.

In clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.