Related papers: Attentive Feature Reuse for Multi Task Meta learni…

We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features…

Current state-of-the-art visual recognition systems usually rely on the following pipeline: (a) pretraining a neural network on a large-scale dataset (e.g., ImageNet) and (b) finetuning the network weights on a smaller, task-specific…

Transformer-based architectures have demonstrated remarkable success across various domains, but their deployment on edge devices remains challenging due to high memory and computational demands. In this paper, we introduce a novel Reuse…

Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote…

We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Unlike existing multi-task learning methodologies, the graph structure is not assumed…

Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning.…

In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting…

Current deep neural networks (DNNs) can easily overfit to biased training data with corrupted labels or class imbalance. Sample re-weighting strategy is commonly used to alleviate this issue by designing a weighting function mapping from…

Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from…

Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called…

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…

We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which…

Multitask learning is a common approach in machine learning, which allows to train multiple objectives with a shared architecture. It has been shown that by training multiple tasks together inference time and compute resources can be saved,…

We address representation learning for large-scale instance-level image retrieval. Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are…

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular…

With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations.…

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of…

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a…