相关论文: Transformation Importance with Applications to Cos…

Real-life medical data is often multimodal and incomplete, fueling the growing need for advanced deep learning models capable of integrating them efficiently. The use of diverse modalities, including histopathology slides, MRI, and genetic…

Convolutional neural networks (CNN) are known for their excellent feature extraction capabilities to enable the learning of models from data, yet are used as black boxes. An interpretation of the convolutional filtres and associated…

Deep learning based localization and mapping has recently attracted significant attention. Instead of creating hand-designed algorithms through exploitation of physical models or geometric theories, deep learning based solutions provide an…

In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction…

Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have…

Deep learning models are used in critical applications, in which mistakes can have serious consequences. Therefore, it is crucial to understand how and why models generate predictions. This understanding provides useful information to check…

Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features. It is crucial to address the curse of dimensionality, enhance model generalization, overcome data sparsity, and…

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

We present Large Inverse Rendering Model (LIRM), a transformer architecture that jointly reconstructs high-quality shape, materials, and radiance fields with view-dependent effects in less than a second. Our model builds upon the recent…

The capacity to transfer knowledge across scientific domains relies on shared organizational principles. However, existing transfer-learning methodologies often fail to bridge radically heterogeneous systems, particularly under severe data…

Robust imitation learning for robot manipulation requires comprehensive 3D perception, yet many existing methods struggle in cluttered environments. Fixed camera view approaches are vulnerable to perspective changes, and 3D point cloud…

Biological intelligence is remarkable in its ability to produce complex behaviour in many diverse situations through data efficient, generalisable and transferable skill acquisition. It is believed that learning "good" sensory…

Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network…

In the realm of semantic communication, the significance of encoded features can vary, while wireless channels are known to exhibit fluctuations across multiple subchannels in different domains. Consequently, critical features may traverse…

Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To…

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…

Robotic tasks such as manipulation with visual inputs require image features that capture the physical properties of the scene, e.g., the position and configuration of objects. Recently, it has been suggested to learn such features in an…

Change detection is a fundamental task in computer vision that processes a bi-temporal image pair to differentiate between semantically altered and unaltered regions. Large language models (LLMs) have been utilized in various domains for…

In machine learning models, the estimation of errors is often complex due to distribution bias, particularly in spatial data such as those found in environmental studies. We introduce an approach based on the ideas of importance sampling to…

LiDAR-based semantic segmentation is a key component for autonomous mobile robots, yet large-scale annotation of LiDAR point clouds is prohibitively expensive and time-consuming. Although simulators can provide labeled synthetic data,…