Related papers: FastCAR: Fast Classification And Regression for Ta…

FastCAR is a novel task consolidation approach in Multi-Task Learning (MTL) for a classification and a regression task, despite task heterogeneity with only subtle correlation. It addresses object classification and continuous property…

Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…

Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these…

In the realm of Earth science, effective cloud property retrieval, encompassing cloud masking, cloud phase classification, and cloud optical thickness (COT) prediction, remains pivotal. Traditional methodologies necessitate distinct models…

Digitising the 3D world into a clean, CAD model-based representation has important applications for augmented reality and robotics. Current state-of-the-art methods are computationally intensive as they individually encode each detected…

In many practical applications of supervised learning the task involves the prediction of multiple target variables from a common set of input variables. When the prediction targets are binary the task is called multi-label classification,…

Upon the significant performance of the supervised deep neural networks, conventional procedures of developing ML system are \textit{task-centric}, which aims to maximize the task accuracy. However, we scrutinized this \textit{task-centric}…

Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most…

The search for predictive models that generalize to the long tail of sensor inputs is the central difficulty when developing data-driven models for autonomous vehicles. In this paper, we use lane detection to study modeling and training…

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling…

Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding…

Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple…

Recent algorithms in convolutional neural networks (CNN) considerably advance the fine-grained image classification, which aims to differentiate subtle differences among subordinate classes. However, previous studies have rarely focused on…

Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for assessing data informativeness often fail to align directly…

In recent years, several progressive works promote the development of aerial tracking. One of the representative works is our previous work Fast-tracker which is applicable to various challenging tracking scenarios. However, it suffers from…

Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have…

As an effective learning paradigm against insufficient training samples, Multi-Task Learning (MTL) encourages knowledge sharing across multiple related tasks so as to improve the overall performance. In MTL, a major challenge springs from…

Most information in our world is organized hierarchically; however, many Deep Learning approaches do not leverage this semantically rich structure. Research suggests that human learning benefits from exploiting the hierarchical structure of…

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…