相关论文: A Dual-Branch Local-Global Framework for Cross-Res…

Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms…

In this work, we address the challenge of multi-domain translation, where the objective is to learn mappings between arbitrary configurations of domains within a defined set (such as $(D_1, D_2)\rightarrow{}D_3$, $D_2\rightarrow{}(D_1,…

Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge across domains. Disentangled representation learning provides an effective solution to model complex user preferences by separating intra-domain…

Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising,…

Domain alignment in convolutional networks aims to learn the degree of layer-specific feature alignment beneficial to the joint learning of source and target datasets. While increasingly popular in convolutional networks, there have been no…

The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For…

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…

Synthetic data provide low-cost, accurately annotated samples for geometry-sensitive vision tasks, but appearance and imaging differences between synthetic and real domains cause severe domain shift and degrade downstream performance.…

Recently, there has been an increased interest in the practical problem of learning multiple dense scene understanding tasks from partially annotated data, where each training sample is only labeled for a subset of the tasks. The missing of…

Weakly supervised segmentation methods can delineate thyroid nodules in ultrasound images efficiently using training data with coarse labels, but suffer from: 1) low-confidence pseudo-labels that follow topological priors, introducing…

Document expansion (DE) via query generation tackles vocabulary mismatch in sparse retrieval, yet faces limitations: uncontrolled generation producing hallucinated or redundant queries with low diversity; poor generalization from in-domain…

Semi-supervised semantic segmentation focuses on the exploration of a small amount of labeled data and a large amount of unlabeled data, which is more in line with the demands of real-world image understanding applications. However, it is…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits…

DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of…

Accurate beam alignment is a critical challenge in XL-MIMO systems, especially in the near-field regime, where conventional far-field assumptions no longer hold. Although 2D grid-based codebooks in the polar domain are widely accepted for…

The goal of video anomaly detection is tantamount to performing spatio-temporal localization of abnormal events in the video. The multiscale temporal dependencies, visual-semantic heterogeneity, and the scarcity of labeled data exhibited by…

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degradation in unusual scenes. Unfortunately, different datasets…

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

Off-road semantic segmentation is fundamentally challenged by irregular terrain, vegetation clutter, and inherent annotation ambiguity. Unlike urban scenes with crisp object boundaries, off-road environments exhibit strong class-level…