Related papers: Towards Robust Adaptive Object Detection under Noi…

Deep learning in the presence of noisy annotations has been studied extensively in classification, but much less in segmentation tasks. In this work, we study the learning dynamics of deep segmentation networks trained on…

Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset without any further annotations. Most successful UDA-ReID approaches combine…

Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain…

Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotation. Recent studies have explored weakly and semi-supervised…

Training a deep neural network heavily relies on a large amount of training data with accurate annotations. To alleviate this problem, various methods have been proposed to annotate the data automatically. However, automatically generating…

In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods typically follow a two-stage optimization pipeline, where the…

One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations,…

The performance of object detection, to a great extent, depends on the availability of large annotated datasets. To alleviate the annotation cost, the research community has explored a number of ways to exploit unlabeled or weakly labeled…

Semi-Supervised Domain Adaptation (SSDA) involves learning to classify unseen target data with a few labeled and lots of unlabeled target data, along with many labeled source data from a related domain. Current SSDA approaches usually aim…

Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.…

The growing demand for oriented object detection (OOD) across various domains has driven significant research in this area. However, the high cost of dataset annotation remains a major concern. Current mainstream OOD algorithms can be…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

In this paper, we introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning, which arise from dependencies on instances and labels.…

Labeled data is a fundamental component in training supervised deep learning models for computer vision tasks. However, the labeling process, especially for ordinal image classification where class boundaries are often ambiguous, is prone…

Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple…

Various deep learning models have been developed for indoor localization based on radio-frequency identification (RFID) tags. However, they often require adaptation to ensure accurate tracking in new target operational domains. To address…

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

While the volume of remote sensing data is increasing daily, deep learning in Earth Observation faces lack of accurate annotations for supervised optimization. Crowdsourcing projects such as OpenStreetMap distribute the annotation load to…

With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limitation of current training datasets is their reliance on…