24 papers · ranked by Valyu relevance
Yongqin Xian, Bernt Schiele, Zeynep Akata
Due to the importance of zero-shot learning, the number of proposed approaches has increased steadily recently. We argue that it is time to take a step back and to analyze the status quo of the area. The purpose of this paper is threefold. First, given the fact that there is no agreed upon zeroshot learning benchmark…
Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu + 2 more
Modeling the effect of sequence variation on function is a fundamental problem for understanding and designing proteins. Since evolution encodes information about function into patterns in protein sequences, unsupervised models of variant effects can be learned from sequence data. The approach to date has been to fit a…
Kai Li, Martin Renqiang Min, Yun Fu
Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from one feature space to the other. Despite being reasonable, previous approaches…
Yu Shi, Wei Xu, Pingzhao Hu
In the dynamic and complex field of bioinformatics, the development of machine learning models capable of accurately predicting and interpreting genomic data underpins many critical applications, from disease diagnosis to drug discovery. Traditional machine learning models, however, often fail when facing with…
Aitor González-Marfil, Estibaliz Gómez-de-Mariscal, Ignacio Arganda-Carreras
We present DINOSim, a novel approach leveraging the DINOv2 pretrained encoder for zero-shot object detection and segmentation in electron microscopy datasets. By exploiting semantic embeddings, DINOSim generates pseudo-labels from patch distances to a user-selected reference, which are subsequently employed in a…
Huabo Shen, Xiaodong Sun, Youmin Hu, Changgeng Li + 3 more
Zero-shot learning (ZSL) aims to classify unseen classes by leveraging semantic information from seen classes, addressing the challenge of limited labeled data. In recent years, ZSL methods have focused on extracting attribute-level features from images and aligning them with semantic features within an embedding…
Umm-e-Hani Tayyab, Faiza Babar Khan, Asifullah Khan, Muhammad Hanif Durad + 3 more
Effective malware detection is critical to safeguarding digital ecosystems from evolving cyber threats. However, the scarcity of labeled training data, particularly for cross-family malware detection, poses a significant challenge. This research proposes a novel architecture ConvNet-6 to be used in Siamese Neural…
Ysobel Sims, Stephan K. Chalup, Alexandre Mendes
—Zero-shot learning enables models to generalize to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes. While much research has focused on zero-shot learning in computer vision, the application of these methods to environmental audio…
Jingyi Liu, Caijuan Shi, Dongjing Tu, Ze Shi + 3 more
'Kang-Ryoung Park'] The supervised model based on deep learning has made great achievements in the field of image classification after training with a large number of labeled samples. However, there are many categories without or only with a few labeled training samples in practice, and some categories even have no…
Iman Deznabi, Busra Arabaci, Mehmet Koyutürk, Oznur Tastan
Protein phosphorylation is a key regulator of protein function in signal transduction pathways. Kinases are the enzymes that catalyze the phosphorylation of other proteins in a target specific manner. The dysregulation of phosphorylation is associated with many diseases including cancer. Although the advances in…
Bo Zhao, Xinwei Sun, Yuan Yao, Yizhou Wang
Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structuretransfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic embedding space to image feature space to classify testing images. However, we observe…
Xun Xu, Timothy M. Hospedales, Shaogang Gong
The number of categories for action recognition is growing rapidly and it has become increasingly hard to label sufficient training data for learning conventional models for all categories. Instead of collecting ever more data and labelling them exhaustively for all categories, an attractive alternative approach is…
Hongguang Zhang, Piotr Koniusz
In this paper, we address an open problem of zero-shot learning. Its principle is based on learning a mapping that associates feature vectors extracted from i.e. images and attribute vectors that describe objects and/or scenes of interest. In turns, this allows classifying unseen object classes and/or scenes by…
Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang + 2 more
'Timothy M. Hospedales'] We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to…
Beibei Yu, Cheng Xie, Peng Tang, Bin Li + 1 more
Almost all existing zero-shot learning methods work only on benchmark datasets (e.g., CUB, SUN, AwA, FLO and aPY) which have already provided pre-defined attributes for all the classes. These methods thus are hard to apply on real-world datasets (like ImageNet) since there are no such pre-defined attributes in the data…
Ning Wang, Yu Long, Cong Hua, Guangming Zhu + 4 more
—Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance…
Thomas P. O’Connell, Marvin M. Chun, Gabriel Kreiman
Decoding information from neural responses in visual cortex demonstrates interpolation across repetitions or exemplars. Is it possible to decode novel categories from neural activity without any prior training on activity from those categories? We built zero-shot neural decoders by mapping responses from macaque…
Ben Sorscher, Surya Ganguli, Haim Sompolinsky
Understanding the neural basis of our remarkable cognitive capacity to accurately learn novel high-dimensional naturalistic concepts from just one or a few sensory experiences constitutes a fundamental problem. We propose a simple, biologically plausible, mathematically tractable, and computationally powerful neural…
Hiroki Ohashi, Mohammad Al-Naser, Sheraz Ahmed, Katsuyuki Nakamura + 2 more
This paper presents a simple yet effective method for improving the performance of zero-shot learning (ZSL). ZSL classifies instances of unseen classes, from which no training data is available, by utilizing the attributes of the classes. Conventional ZSL methods have equally dealt with all the available attributes…
Authors not listed
Molecular property prediction is a fundamental task in computational chemistry with critical applications in drug discovery and materials science. While recent works have explored Large Language Models (LLMs) for this task, they primarily rely on textual molecular representations such as SMILES/SELFIES, which can be…
Derek van Tilborg, Francesca Grisoni
Deep learning is accelerating drug discovery. However, current approaches are often affected by limitations in the available data, e.g., in terms of size or molecular diversity. Active deep learning has an untapped potential for low-data drug discovery, as it allows to improve a model iteratively during the screening…
Derek van Tilborg, Helena Brinkmann, Emanuele Criscuolo, Luke Rossen + 2 more
Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches – which are notoriously…
Rachana Niranjan Murthy, Sai Teja Potu, Akhil Thomas, Lokesh Mishra + 2 more
Retrieving structured materials information from unstructured textual data is essential for data mining and automatically developing comprehensive ontologies. Information extraction is a complex task composed of multiple subtasks and thus often relies on systems of task-specialized language models. A foundation…
Hosein Fooladi, Steffen Hirte, Johannes Kirchmair
Today, machine learning methods are widely employed in drug discovery. However, the chronic lack of data continues to hamper their further development, validation, and application. Several modern strategies aim to mitigate the challenges associated with data scarcity by learning from data on related tasks. These…