Related papers: Robust Synthetic-to-Real Transfer for Stereo Match…
Traditional face super-resolution (FSR) methods trained on synthetic datasets usually have poor generalization ability for real-world face images. Recent work has utilized complex degradation models or training networks to simulate the real…
The use of pre-trained language models fine-tuned to address specific downstream tasks is a common approach in natural language processing (NLP). However, acquiring domain-specific knowledge via fine-tuning is challenging. Traditional…
Synthetic-to-real data translation using generative adversarial learning has achieved significant success in improving synthetic data. Yet, limited studies focus on deep evaluation and comparison of adversarial training on general-purpose…
Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting…
Self-supervised depth estimation from monocular cameras in diverse outdoor conditions, such as daytime, rain, and nighttime, is challenging due to the difficulty of learning universal representations and the severe lack of labeled…
A common way to use large pre-trained language models for downstream tasks is to fine tune them using additional layers. This may not work well if downstream domain is a specialized domain whereas the large language model has been…
Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it can reduce the need for costly data annotation. Yet, synthetic and real world data have a domain gap. Reducing…
Preference tuning aligns pretrained language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Prior work has shown that preference-tuning degrades…
In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the…
Deep learning-based solutions for semantic segmentation suffer from significant performance degradation when tested on data with different characteristics than what was used during the training. Adapting the models using annotated data from…
Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…
Prior feature transformation based approaches to Unsupervised Domain Adaptation (UDA) employ the deep features extracted by pre-trained deep models without fine-tuning them on the specific source or target domain data for a particular…
Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and…
A widely used algorithm for transfer learning is fine-tuning, where a pre-trained model is fine-tuned on a target task with a small amount of labeled data. When the capacity of the pre-trained model is significantly larger than the size of…
End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even…
Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite…
Reconstructing low-dimensional truth labels from high-dimensional experimental data is a central challenge in any scenario that relies on robust mappings across this so-called domain gap, from multi-particle final states in high-energy…
Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is…
Deep learning based image enhancement models have largely improved the readability of fundus images in order to decrease the uncertainty of clinical observations and the risk of misdiagnosis. However, due to the difficulty of acquiring…
Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by first training a teacher model on source domain labeled…