Related papers: Disentangling Task Relations for Few-shot Text Cla…

Auxiliary tasks facilitate learning in situations where data is scarce or the principal task of interest is extremely complex. This idea is primarily inspired by the improved generalization capability induced by solving multiple tasks…

In clustering tasks, it is essential to structure the feature space into clear, well-separated distributions. However, because short text representations have limited expressiveness, conventional methods struggle to identify cluster centers…

Hierarchical clustering is a popular unsupervised data analysis method. For many real-world applications, we would like to exploit prior information about the data that imposes constraints on the clustering hierarchy, and is not captured by…

In this thesis, we propose a light-weight sparsity-based algorithm, basic thresholding classifier (BTC), for classification applications (such as face identification, hyper-spectral image classification, etc.) which is capable of…

Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for the target object using the support set is essential for…

Multi-Task Learning (MTL) is a powerful technique that has gained popularity due to its performance improvement over traditional Single-Task Learning (STL). However, MTL is often challenging because there is an exponential number of…

Clustering temporal and dynamically changing multivariate time series from real-world fields, called temporal clustering for short, has been a major challenge due to inherent complexities. Although several deep temporal clustering…

Due to computational and storage efficiencies of compact binary codes, hashing has been widely used for large-scale similarity search. Unfortunately, many existing hashing methods based on observed keyword features are not effective for…

Achieving state-of-the-art performance on natural language understanding tasks typically relies on fine-tuning a fresh model for every task. Consequently, this approach leads to a higher overall parameter cost, along with higher technical…

Multi-step manipulation tasks where robots interact with their environment and must apply process forces based on the perceived situation remain challenging to learn and prone to execution errors. Accurately simulating these tasks is also…

Hierarchical clustering is one of the most powerful solutions to the problem of clustering, on the grounds that it performs a multi scale organization of the data. In recent years, research on hierarchical clustering methods has attracted…

Camera-based 3D semantic scene completion (SSC) is pivotal for predicting complicated 3D layouts with limited 2D image observations. The existing mainstream solutions generally leverage temporal information by roughly stacking history…

Multi-label text classification (MLTC) tasks in the medical domain often face the long-tail label distribution problem. Prior works have explored hierarchical label structures to find relevant information for few-shot classes, but mostly…

With the advent of semantic web, various tools and techniques have been introduced for presenting and organizing knowledge. Concept hierarchies are one such technique which gained significant attention due to its usefulness in creating…

Wireless sensor networks (WSNs) suffers from the hot spot problem where the sensor nodes closest to the base station are need to relay more packet than the nodes farther away from the base station. Thus, lifetime of sensory network depends…

In this paper, we present a new method, Transductive Multi-Head Few-Shot learning (TMHFS), to address the Cross-Domain Few-Shot Learning (CD-FSL) challenge. The TMHFS method extends the Meta-Confidence Transduction (MCT) and Dense…

Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…

Hierarchical clustering (HC) algorithms are generally limited to small data instances due to their runtime costs. Here we mitigate this shortcoming and explore fast HC algorithms based on random projections for single (SLC) and average…

The increased availability of massive point clouds coupled with their utility in a wide variety of applications such as robotics, shape synthesis, and self-driving cars has attracted increased attention from both industry and academia.…

Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…