相关论文: Domain Adaptation with Morphologic Segmentation

Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works. However, the domain shifts/discrepancies problem in this task compromise the final…

In this paper, we present the submission to the 5th Annual Smoky Mountains Computational Sciences Data Challenge, Challenge 3. This is the solution for semantic segmentation problem in both real-world and synthetic images from a vehicle s…

Image-to-image translation architectures may have limited effectiveness in some circumstances. For example, while generating rainy scenarios, they may fail to model typical traits of rain as water drops, and this ultimately impacts the…

Modern image generative models show remarkable sample quality when trained on a single domain or class of objects. In this work, we introduce a generative adversarial network that can simultaneously generate aligned image samples from…

Semantic segmentation with dense pixel-wise annotation has achieved excellent performance thanks to deep learning. However, the generalization of semantic segmentation in the wild remains challenging. In this paper, we address the problem…

Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for this task: 1) lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we…

We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and stuffs) in an image without predicting their semantic labels. By removing the need of class label…

The ability to segment unknown objects in cluttered scenes has a profound impact on robot grasping. The rise of deep learning has greatly transformed the pipeline of robotic grasping from model-based approach to data-driven stream, which…

The aim of this paper is to give an overview of domain adaptation and transfer learning with a specific view on visual applications. After a general motivation, we first position domain adaptation in the larger transfer learning problem.…

Domain adaptation, a pivotal branch of transfer learning, aims to enhance the performance of machine learning models when deployed in target domains with distinct data distributions. This is particularly critical for object detection tasks,…

Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convolutional Neural Networks trained on supervised tasks with…

We propose a universal image reconstruction method to represent detailed images purely from binary sparse edge and flat color domain. Inspired by the procedures of painting, our framework, based on generative adversarial network, consists…

We present a general framework for exemplar-based image translation, which synthesizes a photo-realistic image from the input in a distinct domain (e.g., semantic segmentation mask, or edge map, or pose keypoints), given an exemplar image.…

Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism…

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

Minimization of distribution matching losses is a principled approach to domain adaptation in the context of image classification. However, it is largely overlooked in adapting segmentation networks, which is currently dominated by…

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…

Current successful approaches for generic (non-semantic) segmentation rely mostly on edge detection and have leveraged the strengths of deep learning mainly by improving the edge detection stage in the algorithmic pipeline. This is in…

Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated…

The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain…