Related papers: DATA: Domain-And-Time Alignment for High-Quality F…

Current state-of-the-art vision models often utilize feature pyramids to extract multi-scale information, with the Feature Pyramid Network (FPN) being one of the most widely used classic architectures. However, traditional FPNs and their…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

This paper tackles a novel yet challenging problem: how to transfer knowledge from the emerging Segment Anything Model (SAM) -- which reveals impressive zero-shot instance segmentation capacity -- to learn a compact panoramic semantic…

Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render…

Multispectral (MS) and panchromatic (PAN) images describe the same land surface, so these images not only have their own advantages, but also have a lot of similar information. In order to separate these similar information and their…

Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers. In…

Despite the significant progress made by deep learning in natural image matting, there has been so far no representative work on deep learning for video matting due to the inherent technical challenges in reasoning temporal domain and lack…

Image fusion aims to generate a high-quality image from multiple images captured under varying conditions. The key problem of this task is to preserve complementary information while filtering out irrelevant information for the fused…

The recovery of 3D human mesh from monocular images has significantly been developed in recent years. However, existing models usually ignore spatial and temporal information, which might lead to mesh and image misalignment and temporal…

Real-world applications of machine learning models often confront data distribution shifts, wherein discrepancies exist between the training and test data distributions. In the common multi-domain multi-class setup, as the number of classes…

Feature matching between image pairs is a fundamental problem in computer vision that drives many applications, such as SLAM. Recently, semi-dense matching approaches have achieved substantial performance enhancements and established a…

Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Remote sensing change detection is often challenged by spatial misalignment between bi-temporal images, especially when acquisitions are separated by long seasonal or multi-year gaps. While modern convolutional and transformer-based models…

We propose a novel method that tackles the problem of unsupervised domain adaptation for semantic segmentation by maximizing the cosine similarity between the source and the target domain at the feature level. A segmentation network mainly…

Considerable research attention has been paid to table detection by developing not only rule-based approaches reliant on hand-crafted heuristics but also deep learning approaches. Although recent studies successfully perform table detection…

In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making. However, object motion and ego-motion often induce cross-frame spatiotemporal inconsistencies in BEV-based detectors, leading to…

Although data is abundant, data labeling is expensive. Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models. This paper introduces our proposed method LiDAM, a…

While deep learning has reduced the prevalence of manual feature extraction, transformation of data via feature engineering remains essential for improving model performance, particularly for underwater acoustic signals. The methods by…

Domain generalization (DG) aims to learn from multiple known source domains a model that can generalize well to unknown target domains. The existing DG methods usually exploit the fusion of shared multi-source data to train a generalizable…