Related papers: SIGMAE: A Spectral-Index-Guided Foundation Model f…
There has long been a belief that high-level semantics learning can benefit various downstream computer vision tasks. However, in the low-light image enhancement (LLIE) community, existing methods learn a brutal mapping between low-light…
LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…
Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., either images or point…
Semantic Segmentation combines two sub-tasks: the identification of pixel-level image masks and the application of semantic labels to those masks. Recently, so-called Foundation Models have been introduced; general models trained on very…
Redshift prediction is a fundamental task in astronomy, essential for understanding the expansion of the universe and determining the distances of astronomical objects. Accurate redshift prediction plays a crucial role in advancing our…
Multi-modal learning adeptly integrates visual and textual data, but its application to histopathology image and text analysis remains challenging, particularly with large, high-resolution images like gigapixel Whole Slide Images (WSIs).…
Multiview systems have become a key technology in modern computer vision, offering advanced capabilities in scene understanding and analysis. However, these systems face critical challenges in bandwidth limitations and computational…
Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning (masking ratio, patch size, encoder/decoder layers) when…
Neural network approaches to single-channel speech enhancement have received much recent attention. In particular, mask-based architectures have achieved significant performance improvements over conventional methods. This paper proposes a…
Human Action Recognition using WiFi Channel State Information (CSI) has emerged as an attractive alternative to vision-based methods due to its ubiquity, device-agnostic nature, and inherent privacy-preserving capabilities. However, the…
Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…
With the development of deep learning, supervised learning methods perform well in remote sensing images (RSIs) scene classification. However, supervised learning requires a huge number of annotated data for training. When labeled samples…
Spectral imaging data acquired via multispectral and hyperspectral cameras can have hundreds of channels, where each channel records the reflectance at a specific wavelength and bandwidth. Time and resource constraints limit our ability to…
Traditional radio map estimation (RME) techniques fail to capture multi-dimensional and dynamic characteristics of complex spectrum environments. Recent data-driven methods achieve accurate RME in spatial domain, but ignore physical prior…
Self-supervised learning (SSL) has gained widespread attention in the remote sensing (RS) and earth observation (EO) communities owing to its ability to learn task-agnostic representations without human-annotated labels. Nevertheless, most…
Infrared and visible image fusion (IVIF) is essential for integrating thermal saliency with textural details to support downstream perception. However, most existing approaches suffer from "semantic blindness," leading to the erroneous…
We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models. Instead of randomly inserting mask tokens to the input embeddings in the spatial domain, in this paper,…
Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…
Deep learning methodology contributes a lot to the development of hyperspectral image (HSI) analysis community. However, it also makes HSI analysis systems vulnerable to adversarial attacks. To this end, we propose a masked spatial-spectral…
In medical image analysis, the cost of acquiring high-quality data and their annotation by experts is a barrier in many medical applications. Most of the techniques used are based on supervised learning framework and need a large amount of…