Related papers: SCA-Net: A Self-Correcting Two-Layer Autoencoder f…

Parameter-efficient fine-tuning of pre-trained codecs is a promising direction in image compression for human and machine vision. While most existing works have primarily focused on tuning the feature structure within the encoder-decoder…

End-to-end Automatic Speech Recognition (ASR) models are usually trained to optimize the loss of the whole token sequence, while neglecting explicit phonemic-granularity supervision. This could result in recognition errors due to…

The underlying dynamics and patterns of 3D surface meshes deforming over time can be discovered by unsupervised learning, especially autoencoders, which calculate low-dimensional embeddings of the surfaces. To study the deformation patterns…

In this paper, we propose a methodology for extracting molecular tumor biomarkers from hyperspectral imaging (HSI), an emerging technology for intraoperative tissue assessment. To achieve this, we employ spectral unmixing, allowing to…

Massive MIMO is currently a leading physical layer technology candidate that can dramatically enhance throughput in 5G systems, for both unicast and multicast transmission modalities. As antenna elements are becoming smaller and cheaper in…

Autoencoders are unsupervised machine learning circuits whose learning goal is to minimize a distortion measure between inputs and outputs. Linear autoencoders can be defined over any field and only real-valued linear autoencoder have been…

We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during…

Sparse autoencoders (SAEs) have been used widely to decompose and interpret neural network activations, especially those of transformer language models. One key issue with SAEs is their inability to directly model multidimensional features.…

Although hyperspectral image (HSI) classification is critical for supporting various environmental applications, it is a challenging task due to the spectral-mixture effect, the spatial-spectral heterogeneity and the difficulty to preserve…

To improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data. We show that these two approaches, at…

Biomedical image segmentation plays a significant role in computer-aided diagnosis. However, existing CNN based methods rely heavily on massive manual annotations, which are very expensive and require huge human resources. In this work, we…

Semi-supervised change detection (SSCD) aims to detect changes between bi-temporal remote sensing images by utilizing limited labeled data and abundant unlabeled data. Existing methods struggle in complex scenarios, exhibiting poor…

Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Research in the past years introduced Steered Mixture-of-Experts (SMoE) as a framework to form sparse, edge-aware models for 2D- and higher dimensional pixel data, applicable to compression, denoising, and beyond, and capable to compete…

Prior Arbitrary-Scale Image Super-Resolution (ASISR) methods often experience a significant performance decline when the upsampling factor exceeds the range covered by the training data, introducing substantial blurring. To address this…

Due to the limitations of hyperspectral imaging systems, hyperspectral imagery (HSI) often suffers from poor spatial resolution, thus hampering many applications of the imagery. Hyperspectral super-resolution refers to fusing HSI and MSI to…

Unsupervised Anomaly Detection has become a popular method to detect pathologies in medical images as it does not require supervision or labels for training. Most commonly, the anomaly detection model generates a "normal" version of an…

Recent works show that overparameterized networks contain small subnetworks that exhibit comparable accuracy to the full model when trained in isolation. These results highlight the potential to reduce training costs of deep neural networks…

Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image…