Related papers: Contrastive Masked Autoencoders for Character-Leve…

Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed…

Over the years, state-of-the-art (SoTA) image captioning methods have achieved promising results on some evaluation metrics (e.g., CIDEr). However, recent findings show that the captions generated by these methods tend to be biased toward…

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…

Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained…

The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…

Recently, scene text recognition (STR) models have shown significant performance improvements. However, existing models still encounter difficulties in recognizing challenging texts that involve factors such as severely distorted and…

In surface defect detection, due to the extreme imbalance in the number of positive and negative samples, positive-samples-based anomaly detection methods have received more and more attention. Specifically, reconstruction-based methods are…

Network traffic classification using self-supervised pre-training models based on Masked Autoencoders (MAE) has demonstrated a huge potential. However, existing methods are confined to isolated byte-level reconstruction of individual flows,…

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a…

Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…

Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful…

Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-encoder utilizes contextual embedding to assist in the…

To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on…

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…

Despite its practical importance across a wide range of modalities, recent advances in self-supervised learning (SSL) have been primarily focused on a few well-curated domains, e.g., vision and language, often relying on their…

Federated learning is a specific distributed learning paradigm in which a central server aggregates updates from multiple clients' local models, thereby enabling the server to learn without requiring clients to upload their private data,…

Extracting fine-grained features such as styles from unlabeled data is crucial for data analysis. Unsupervised methods such as variational autoencoders (VAEs) can extract styles that are usually mixed with other features. Conditional VAEs…

Facial expression recognition (FER) has emerged as an important component of human-computer interaction systems. Despite recent advancements in FER, performance often drops significantly for non-frontal facial images. We propose Contrastive…

In the contrastive analysis (CA) setting, machine learning practitioners are specifically interested in discovering patterns that are enriched in a target dataset as compared to a background dataset generated from sources of variation…