Related papers: TaskExpert: Dynamically Assembling Multi-Task Repr…

Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios. However, relying solely on a single vision encoder to handle…

In clinical scenarios, multi-specialist consultation could significantly benefit the diagnosis, especially for intricate cases. This inspires us to explore a "multi-expert joint diagnosis" mechanism to upgrade the existing "single expert"…

Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…

Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional…

Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all samples. Whereas high complexity models are proven to be…

In this study, we show that landmark detection or face alignment task is not a single and independent problem. Instead, its robustness can be greatly improved with auxiliary information. Specifically, we jointly optimize landmark detection…

In this work we present a Mixture of Task-Aware Experts Network for Machine Reading Comprehension on a relatively small dataset. We particularly focus on the issue of common-sense learning, enforcing the common ground knowledge by…

Recent advancements in all-in-one image restoration models have revolutionized the ability to address diverse degradations through a unified framework. However, parameters tied to specific tasks often remain inactive for other tasks, making…

Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible. However, the matching task aims at describing the corresponding points consistently…

Multi-task dense prediction aims at handling multiple pixel-wise prediction tasks within a unified network simultaneously for visual scene understanding. However, cross-task feature interactions of current methods are still suffering from…

Detecting manipulated images and videos is an important topic in digital media forensics. Most detection methods use binary classification to determine the probability of a query being manipulated. Another important topic is locating…

Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task…

Recent progress in computer vision has produced a wide range of powerful specialized models for detection, segmentation, counting, and other visual tasks. However, these models are usually optimized for isolated task formulations, making it…

Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed…

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense…

Recent studies have focused on utilizing multi-modal data to develop robust models for facial Action Unit (AU) detection. However, the heterogeneity of multi-modal data poses challenges in learning effective representations. One such…

The perception system for autonomous driving generally requires to handle multiple diverse sub-tasks. However, current algorithms typically tackle individual sub-tasks separately, which leads to low efficiency when aiming at obtaining…

This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by…