Related papers: Self-supervised Detransformation Autoencoder for R…

The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks. While there has been excellent progress with simple, image-level learning, recent methods have shown the advantage of…

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Anomaly detection in tabular data remains challenging due to complex feature interactions and the scarcity of anomalous examples. Denoising autoencoders rely on fixed-magnitude noise, limiting adaptability to diverse data distributions.…

Text style transfer aims to change the style of sentences while preserving the semantic meanings. Due to the lack of parallel data, the Denoising Auto-Encoder (DAE) is widely used in this task to model distributions of different sentence…

Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…

High-dimensional data, particularly in the form of high-order tensors, presents a major challenge in self-supervised learning. While MLP-based autoencoders (AE) are commonly employed, their dependence on flattening operations exacerbates…

Learning disentangled representation from any unlabelled data is a non-trivial problem. In this paper we propose Information Maximising Autoencoder (InfoAE) where the encoder learns powerful disentangled representation through maximizing…

In many imaging modalities, objects of interest can occur in a variety of locations and poses (i.e. are subject to translations and rotations in 2d or 3d), but the location and pose of an object does not change its semantics (i.e. the…

The encoder-decoder dialog model is one of the most prominent methods used to build dialog systems in complex domains. Yet it is limited because it cannot output interpretable actions as in traditional systems, which hinders humans from…

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…

In open-set recognition, existing methods generally learn statically fixed decision boundaries using known classes to reject unknown classes. Though they have achieved promising results, such decision boundaries are evidently insufficient…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

In this work, we propose a novel convolutional autoencoder based architecture to generate subspace specific feature representations that are best suited for classification task. The class-specific data is assumed to lie in low dimensional…

Many real-world monitoring and surveillance applications require non-trivial anomaly detection to be run in the streaming model. We consider an incremental-learning approach, wherein a deep-autoencoding (DAE) model of what is normal is…

We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to…

Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g.~attribute space). However, such a projection function is only concerned with predicting the training…

Image Transformer has recently achieved significant progress for natural image understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) pre-training techniques. In this paper, we propose \textbf{DiT}, a…

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures,…

When applying the foreground removal methods to uncover the faint cosmological signal from the epoch of reionization (EoR), the foreground spectra are assumed to be smooth. However, this assumption can be seriously violated in practice…