相关论文: Self-Supervised Disentanglement by Leveraging Stru…

In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. An intriguing research avenue involves developing…

Data augmentation is a key element in training high-dimensional models. In this approach, one synthesizes new observations by applying pre-specified transformations to the original training data; e.g.~new images are formed by rotating old…

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to…

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…

Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the…

Image matting requires high-quality pixel-level human annotations to support the training of a deep model in recent literature. Whereas such annotation is costly and hard to scale, significantly holding back the development of the research.…

This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence…

Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This…

Intelligent perception and interaction with the world hinges on internal representations that capture its underlying structure (''disentangled'' or ''abstract'' representations). Disentangled representations serve as world models, isolating…

A novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. State-of-the-art model performance and increased…

Stock trend forecasting has become a popular research direction that attracts widespread attention in the financial field. Though deep learning methods have achieved promising results, there are still many limitations, for example, how to…

Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of…

Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimization and feature retention can only be achieved under…

To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models…

Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification, style transfer and sentence generation, among others. The existent dominant approaches in the context of text…

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disentangled representations were found to be useful for diverse…

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…