Related papers: Astromer 2

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2…

Changes of camera perspective are a common obstacle in driver monitoring. While deep learning and pretrained foundation models show strong potential for improved generalization via lightweight adaptation of the final layers ('probing'),…

Deep learning has revolutionized the field of hyperspectral image (HSI) analysis, enabling the extraction of complex spectral and spatial features. While convolutional neural networks (CNNs) have been the backbone of HSI classification,…

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in…

Molecular representation is a critical element in our understanding of the physical world and the foundation for modern molecular machine learning. Previous molecular machine learning models have employed strings, fingerprints, global…

In autonomous embedded systems, it is often vital to reduce the amount of actions taken in the real world and energy required to learn a policy. Training reinforcement learning agents from high dimensional image representations can be very…

While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…

Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate the likeness of voices and faces following contrastive…

Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation…

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

Transformers have made remarkable progress towards modeling long-range dependencies within the medical image analysis domain. However, current transformer-based models suffer from several disadvantages: (1) existing methods fail to capture…

Large occlusions result in a significant decline in image classification accuracy. During inference, diverse types of unseen occlusions introduce out-of-distribution data to the classification model, leading to accuracy dropping as low as…

Clustering is essential to many tasks in pattern recognition and computer vision. With the advent of deep learning, there is an increasing interest in learning deep unsupervised representations for clustering analysis. Many works on this…

Many deep neural networks are susceptible to minute perturbations of images that have been carefully crafted to cause misclassification. Ideally, a robust classifier would be immune to small variations in input images, and a number of…

Deep convolutional neural networks have achieved remarkable success in face recognition (FR), partly due to the abundant data availability. However, the current training benchmarks exhibit an imbalanced quality distribution; most images are…

Multimodal representations that enable cross-modal retrieval are widely used. However, these often lack interpretability making it difficult to explain the retrieved results. Solutions such as learning sparse disentangled representations…

We present a novel two-view geometry estimation framework which is based on a differentiable robust loss function fitting. We propose to treat the robust fundamental matrix estimation as an implicit layer, which allows us to avoid…

Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast…