Related papers: SCENT: Aligning Mass Spectra with Molecular Struct…
Embeddings play an important role in end-to-end solutions for multi-modal language processing problems. Although there has been some effort to understand the properties of single-modality embedding spaces, particularly that of text, their…
Motivation: Tumor classification using Imaging Mass Spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are…
Semantic segmentation and instance level segmentation made substantial progress in recent years due to the emergence of deep neural networks (DNNs). A number of deep architectures with Convolution Neural Networks (CNNs) were proposed that…
We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…
Variability in medical image segmentation, arising from annotator preferences, expertise, and their choice of tools, has been well documented. While the majority of multi-annotator segmentation approaches focus on modeling…
Chemical autoencoders are attractive models as they combine chemical space navigation with possibilities for de-novo molecule generation in areas of interest. This enables them to produce focused chemical libraries around a single lead…
The application of deep learning techniques on aroma-chemicals has resulted in models more accurate than human experts at predicting olfactory qualities. However, public research in this domain has been limited to predicting the qualities…
Accurate segmentation of lesions plays a critical role in medical image analysis and diagnosis. Traditional segmentation approaches that rely solely on visual features often struggle with the inherent uncertainty in lesion distribution and…
Olfactory cues can enhance immersion in interactive media, yet smell remains rare because it is difficult to author and synchronize with dynamic video. Prior olfactory interfaces rely on designer triggers and fixed event-to-odor mappings…
Spectral detection technology, as a non-invasive method for rapid detection of substances, combined with deep learning algorithms, has been widely used in food detection. However, in real scenarios, acquiring and labeling spectral data is…
Entity-level sentiment classification involves identifying the sentiment polarity linked to specific entities within text. This task poses several challenges: effectively modeling the subtle and complex interactions between entities and…
Navigation by scent is a capability in robotic systems that is rising in demand. However, current methods often suffer from ambiguities, particularly when robots misattribute odours to incorrect objects due to limitations in olfactory…
The concept of compressive sensing was recently proposed to significantly reduce the electron dose in scanning transmission electron microscopy (STEM) while still maintaining the main features in the image. Here, an experimental setup based…
Nuclear magnetic resonance (NMR) spectroscopy provides an experimental readout of local chemical environments, but its use in molecular representation learning has been constrained by heterogeneous data and incomplete atom-level…
Predicting electronic energies, densities, and related chemical properties can facilitate the discovery of novel catalysts, medicines, and battery materials. By developing a physics-inspired equivariant neural network, we introduce a method…
Machine learning (ML) codebases face unprecedented challenges in maintaining code quality and sustainability as their complexity grows exponentially. While traditional code smell detection tools exist, they fail to address ML-specific…
Structured embedding transformations offer a promising approach for enhancing the efficiency and coherence of language model inference. The introduction of Structural Embedding Projection (SEP) provides a mechanism for refining token…
Few-shot Semantic Segmentation addresses the challenge of segmenting objects in query images with only a handful of annotated examples. However, many previous state-of-the-art methods either have to discard intricate local semantic features…
Recently, sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks. However, they neglect to evaluate the quality of their constructed sentiment representations; they just…
Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…