Related papers: SePiCo: Semantic-Guided Pixel Contrast for Domain …
Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the…
Domain adaptation (DA) paves the way for label annotation and dataset bias issues by the knowledge transfer from a label-rich source domain to a related but unlabeled target domain. A mainstream of DA methods is to align the feature…
We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain. Our approach explicitly minimizes the distance between the source…
It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict…
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…
In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlying complex structure within scene-centric data; still, they…
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to…
We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains. Our approach draws on…
Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…
In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise…
To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…
Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems. Although state-of-the-art pseudo-label-based methods have…
Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…
Semantic segmentation is an essential step for electron microscopy (EM) image analysis. Although supervised models have achieved significant progress, the need for labor intensive pixel-wise annotation is a major limitation. To complicate…
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…
We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive…
Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…
This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training. Pixel alignment transfers ceT1 scans to hrT2 modality, helping to reduce domain shift in the training segmentation…
Semantic segmentation relies on many dense pixel-wise annotations to achieve the best performance, but owing to the difficulty of obtaining accurate annotations for real world data, practitioners train on large-scale synthetic datasets.…
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…