Related papers: Robust Pseudo-label Learning with Neighbor Relatio…
Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same persons captured by visible (VIS) and infrared (IR) cameras. Existing VI-ReID methods ignore high-order structure information of features while being…
Recent semi-supervised learning (SSL) methods are commonly based on pseudo labeling. Since the SSL performance is greatly influenced by the quality of pseudo labels, mutual learning has been proposed to effectively suppress the noises in…
Person re-identification aims to match a person's identity across multiple camera streams. Deep neural networks have been successfully applied to the challenging person re-identification task. One remarkable bottleneck is that the existing…
Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content contains richer and more reliable semantic information, which remains more robust under…
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and smart cities, without requiring any manual annotation. However,…
Multi-modal object Re-IDentification (ReID) has gained considerable attention with the goal of retrieving specific targets across cameras using heterogeneous visual data sources. At present, multi-modal object ReID faces two core…
We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label…
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…
Semi-supervised 3D object detection (SS3DOD) aims to reduce costly 3D annotations utilizing unlabeled data. Recent studies adopt pseudo-label-based teacher-student frameworks and demonstrate impressive performance. The main challenge of…
Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i.e., source…
Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local data are collected by clients, it is hardly guaranteed that the…
Visible-Infrared person re-identification (VI-ReID) aims to match cross-modality pedestrian images, breaking through the limitation of single-modality person ReID in dark environment. In order to mitigate the impact of large modality…
Cross-modal hashing (CMH) has appeared as a popular technique for cross-modal retrieval due to its low storage cost and high computational efficiency in large-scale data. Most existing methods implicitly assume that multi-modal data is…
User identity linkage, which aims to link identities of a natural person across different social platforms, has attracted increasing research interest recently. Existing approaches usually first embed the identities as deterministic vectors…
A series of unsupervised video-based re-identification (re-ID) methods have been proposed to solve the problem of high labor cost required to annotate re-ID datasets. But their performance is still far lower than the supervised…
Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk…
Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations. Clustering-based methods conduct training with the generated pseudo labels and currently dominate this…
The development of accurate methods for multi-label classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. The MLC methods based on convolutional neural networks (CNNs) have shown strong…
Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently underexplored. Although pairwise training methods have…
Semantic segmentation of SAR images has garnered significant attention in remote sensing due to the immunity of SAR sensors to cloudy weather and light conditions. Nevertheless, SAR imagery lacks detailed information and is plagued by…