We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one. With the goal of generality, we introduce AdaMatch, a method that unifies the tasks of unsupervised domain adaptation (UDA), semi-supervised learning (SSL), and semi-supervised domain adaptation (SSDA). In an extensive experimental study, we compare its behavior with respective state-of-the-art techniques from SSL, SSDA, and UDA on vision classification tasks. We find AdaMatch either matches or significantly exceeds the state-of-the-art in each case using the same hyper-parameters regardless of the dataset or task. For example, AdaMatch nearly doubles the accuracy compared to that of the prior state-of-the-art on the UDA task for DomainNet and even exceeds the accuracy of the prior state-of-the-art obtained with pre-training by 6.4% when AdaMatch is trained completely from scratch. Furthermore, by providing AdaMatch with just one labeled example per class from the target domain (i.e., the SSDA setting), we increase the target accuracy by an additional 6.1%, and with 5 labeled examples, by 13.6%.

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate hallucinated occlusions as well as less confident predictions. Then, a self-supervised learning framework is constructed: confident predictions from teacher models are served as annotations to guide the student model to learn optical flow for those less confident predictions. The self-supervised learning framework enables us to effectively learn optical flow from unlabeled data, not only for non-occluded pixels, but also for occluded pixels. DistillFlow achieves state-of-the-art unsupervised learning performance on both KITTI and Sintel datasets. Our self-supervised pre-trained model also provides an excellent initialization for supervised fine-tuning, suggesting an alternate training paradigm in contrast to current supervised learning methods that highly rely on pre-training on synthetic data. At the time of writing, our fine-tuned models ranked 1st among all monocular methods on the KITTI 2015 benchmark, and outperform all published methods on the Sintel Final benchmark. More importantly, we demonstrate the generalization capability of DistillFlow in three aspects: framework generalization, correspondence generalization and cross-dataset generalization.

Contrastive learning has shown superior performance in embedding global and spatial invariant features in computer vision (e.g., image classification). However, its overall success of embedding local and spatial variant features is still limited, especially for semantic segmentation. In a per-pixel prediction task, more than one label can exist in a single image for segmentation (e.g., an image contains both cat, dog, and grass), thereby it is difficult to define 'positive' or 'negative' pairs in a canonical contrastive learning setting. In this paper, we propose an attention-guided supervised contrastive learning approach to highlight a single semantic object every time as the target. With our design, the same image can be embedded to different semantic clusters with semantic attention (i.e., coerce semantic masks) as an additional input channel. To achieve such attention, a novel two-stage training strategy is presented. We evaluate the proposed method on multi-organ medical image segmentation task, as our major task, with both in-house data and BTCV 2015 datasets. Comparing with the supervised and semi-supervised training state-of-the-art in the backbone of ResNet-50, our proposed pipeline yields substantial improvement of 5.53% and 6.09% in Dice score for both medical image segmentation cohorts respectively. The performance of the proposed method on natural images is assessed via PASCAL VOC 2012 dataset, and achieves 2.75% substantial improvement.

We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation. The proposed method applies aggressive data augmentation (spectral augmentation) on the input of both student and teacher and utilize unlabeled data at scale, which significantly boosts the accuracy of student against challenging conditions. Such aggressive augmentation usually degrades model performance when used with supervised training with hard-labeled data. Experiments show that aggressive spec augmentation on baseline supervised training method degrades accuracy, while the proposed self-training with noisy student-teacher training improves accuracy of some difficult-conditioned test sets by as much as 60%.

Most existing research on domain generalization assumes source data gathered from multiple domains are fully annotated. However, in real-world applications, we might have only a few labels available from each source domain due to high annotation cost, along with abundant unlabeled data that are much easier to obtain. In this work, we investigate semi-supervised domain generalization (SSDG), a more realistic and practical setting. Our proposed approach, StyleMatch, is inspired by FixMatch, a state-of-the-art semi-supervised learning method based on pseudo-labeling, with several new ingredients tailored to solve SSDG. Specifically, 1) to mitigate overfitting in the scarce labeled source data while improving robustness against noisy pseudo labels, we introduce stochastic modeling to the classifier's weights, seen as class prototypes, with Gaussian distributions. 2) To enhance generalization under domain shift, we upgrade FixMatch's two-view consistency learning paradigm based on weak and strong augmentations to a multi-view version with style augmentation as the third complementary view. To provide a comprehensive study and evaluation, we establish two SSDG benchmarks, which cover a wide range of strong baseline methods developed in relevant areas including domain generalization and semi-supervised learning. Extensive experiments demonstrate that StyleMatch achieves the best out-of-distribution generalization performance in the low-data regime. We hope our approach and benchmarks can pave the way for future research on data-efficient and generalizable learning systems.

Semi-supervised learning allows neural networks to mimic human inductive logic and sort unknown information fast and accurately without human intervention. Any problem where you have a large amount of input data but only a few reference points available is a good candidate semi-supervised learning. A classic example is a photo archive with millions of random images. Instead of manually labeling each picture, a human searching for images of people can just tag a few relevant samples from the database. Then the neural network can scour the databank and find every image it believes represents a human.

In previous blog post on supervised learning, we have seen that each observed data has a label attached to it, making it easy to train a model. However, in unsupervised learning, the algorithm finds the hidden patterns in unlabeled data. A popular technique in unsupervised learning is Clustering Algorithms. Clustering Algorithms are a set of algorithms, which clusters data points based on similarity metric either measured in terms of distance or using probability to categorize the data point etc. In simple terms, we can think of clustering as a way to group the data points that are similar in nature from group of data points which are dissimilar.

Risk modeling with EHR data is challenging due to a lack of direct observations on the disease outcome, and the high dimensionality of the candidate predictors. In this paper, we develop a surrogate assisted semi-supervised-learning (SAS) approach to risk modeling with high dimensional predictors, leveraging a large unlabeled data on candidate predictors and surrogates of outcome, as well as a small labeled data with annotated outcomes. The SAS procedure borrows information from surrogates along with candidate predictors to impute the unobserved outcomes via a sparse working imputation model with moment conditions to achieve robustness against mis-specification in the imputation model and a one-step bias correction to enable interval estimation for the predicted risk. We demonstrate that the SAS procedure provides valid inference for the predicted risk derived from a high dimensional working model, even when the underlying risk prediction model is dense and the risk model is mis-specified. We present an extensive simulation study to demonstrate the superiority of our SSL approach compared to existing supervised methods. We apply the method to derive genetic risk prediction of type-2 diabetes mellitus using a EHR biobank cohort.

Machine learning is capable of doing all sorts of things as long as you have the data to teach it how. That's not always easy, and researchers are always looking for a way to add a bit of "common sense" to AI so you don't have to show it 500 pictures of a cat before it gets it. Facebook's newest research takes a big step towards reducing the data bottleneck. The company's formidable AI research division has been working on how to advance and scale things like advanced computer vision algorithms for years now, and has made steady progress, generally shared with the rest of the research community. One interesting development Facebook has pursued in particular is what's called "semi-supervised learning."

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are assigned similar pseudo-labels. The pseudo-labels are generated non-parametrically, by comparing the representations of the image views to those of a set of randomly sampled labeled images. The distance between the view representations and labeled representations is used to provide a weighting over class labels, which we interpret as a soft pseudo-label. By non-parametrically incorporating labeled samples in this way, PAWS extends the distance-metric loss used in self-supervised methods such as BYOL and SwAV to the semi-supervised setting. Despite the simplicity of the approach, PAWS outperforms other semi-supervised methods across architectures, setting a new state-of-the-art for a ResNet-50 on ImageNet trained with either 10% or 1% of the labels, reaching 75.5% and 66.5% top-1 respectively. PAWS requires 4x to 12x less training than the previous best methods.