Related papers: Spectral-Enhanced Transformers: Leveraging Large-S…

Multi-label image classification is about predicting a set of class labels that can be considered as orderless sequential data. Transformers process the sequential data as a whole, therefore they are inherently good at set prediction. The…

Pre-trained deep image representations are useful for post-training tasks such as classification through transfer learning, image retrieval, and object detection. Data augmentations are a crucial aspect of pre-training robust…

Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal…

Enhancing forward-looking sonar images is critical for accurate underwater target detection. Current deep learning methods mainly rely on supervised training with simulated data, but the difficulty in obtaining high-quality real-world…

Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…

Existing single-modal RGB trackers often face performance bottlenecks in complex dynamic scenes, while the introduction of event sensors offers new potential for enhancing tracking capabilities. However, most current RGB-event fusion…

On-board processing of hyperspectral data with machine learning models would enable unprecedented amount of autonomy for a wide range of tasks, for example methane detection or mineral identification. This can enable early warning system…

Accurate and robust tracking of surrounding road participants plays an important role in autonomous driving. However, there is usually no prior knowledge of the number of tracking targets due to object emergence, object disappearance and…

High-Energy Physics experiments are rapidly escalating in generated data volume, a trend that will intensify with the upcoming High-Luminosity LHC upgrade. This surge in data necessitates critical revisions across the data processing…

We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…

Amodal object completion is a complex task that involves predicting the invisible parts of an object based on visible segments and background information. Learning shape priors is crucial for effective amodal completion, but traditional…

There is evidence that transformers offer state-of-the-art recognition performance on tasks involving overhead imagery (e.g., satellite imagery). However, it is difficult to make unbiased empirical comparisons between competing deep…

Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…

Spectral unmixing is one of the most important quantitative analysis tasks in hyperspectral data processing. Conventional physics-based models are characterized by clear interpretation. However they may not be suitable for analyzing scenes…

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the excessive memory…

Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is…

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…

Temporal modeling of objects is a key challenge in multiple object tracking (MOT). Existing methods track by associating detections through motion-based and appearance-based similarity heuristics. The post-processing nature of association…

We apply pre-trained Vision Transformers (ViTs), originally developed for image recognition, to the analysis of astronomical spectral data. By converting traditional one-dimensional spectra into two-dimensional image representations, we…

Deep learning frameworks have become powerful tools for approaching scientific problems such as turbulent flow, which has wide-ranging applications. In practice, however, existing scientific machine learning approaches have difficulty…