Collaborating Authors

(Self-)Supervised Pre-training? Self-training? Which one to use?


Recently, pre-training has been a hot topic in Computer Vision (and also NLP), especially one of the breakthroughs in NLP -- BERT, which proposed a method to train an NLP model by using a "self-supervised" signal. In short, we come up with an algorithm that can generate a "pseudo-label" itself (meaning a label that is true for a specific task), then we treat the learning task as a supervised learning task with the generated pseudo-label. It is commonly called "Pretext Task". For example, BERT uses mask word prediction to train the model (we can then say it is a pre-trained model after it is trained), then fine-tune the model with the task we want (usually called "Downstream Task"), e.g. The mask word prediction is to randomly mask a word in the sentence, and ask the model to predict what is that word given the sentence.

Simultaneous clustering and representation learning


The success of deep learning over the last decade, particularly in computer vision, has depended greatly on large training data sets. Even though progress in this area boosted the performance of many tasks such as object detection, recognition, and segmentation, the main bottleneck for future improvement is more labeled data. Self-supervised learning is among the best alternatives for learning useful representations from the data. In this article, we will briefly review the self-supervised learning methods in the literature and discuss the findings of a recent self-supervised learning paper from ICLR 2020 [14]. We may assume that most learning problems can be tackled by having clean labeling and more data obtained in an unsupervised way.

Local Label Propagation for Large-Scale Semi-Supervised Learning Artificial Intelligence

A significant issue in training deep neural networks to solve supervised learning tasks is the need for large numbers of labelled datapoints. The goal of semi-supervised learning is to leverage ubiquitous unlabelled data, together with small quantities of labelled data, to achieve high task performance. Though substantial recent progress has been made in developing semi-supervised algorithms that are effective for comparatively small datasets, many of these techniques do not scale readily to the large (unlaballed) datasets characteristic of real-world applications. In this paper we introduce a novel approach to scalable semi-supervised learning, called Local Label Propagation (LLP). Extending ideas from recent work on unsupervised embedding learning, LLP first embeds datapoints, labelled and otherwise, in a common latent space using a deep neural network. It then propagates pseudolabels from known to unknown datapoints in a manner that depends on the local geometry of the embedding, taking into account both inter-point distance and local data density as a weighting on propagation likelihood. The parameters of the deep embedding are then trained to simultaneously maximize pseudolabel categorization performance as well as a metric of the clustering of datapoints within each psuedo-label group, iteratively alternating stages of network training and label propagation. We illustrate the utility of the LLP method on the ImageNet dataset, achieving results that outperform previous state-of-the-art scalable semi-supervised learning algorithms by large margins, consistently across a wide variety of training regimes. We also show that the feature representation learned with LLP transfers well to scene recognition in the Places 205 dataset.

Multiview Pseudo-Labeling for Semi-supervised Learning from Video Artificial Intelligence

We present a multiview pseudo-labeling approach to video learning, a novel framework that uses complementary views in the form of appearance and motion information for semi-supervised learning in video. The complementary views help obtain more reliable pseudo-labels on unlabeled video, to learn stronger video representations than from purely supervised data. Though our method capitalizes on multiple views, it nonetheless trains a model that is shared across appearance and motion input and thus, by design, incurs no additional computation overhead at inference time. On multiple video recognition datasets, our method substantially outperforms its supervised counterpart, and compares favorably to previous work on standard benchmarks in self-supervised video representation learning.

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples Artificial Intelligence

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.