Related papers: Generalized Focal Loss: Learning Qualified and Dis…

Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various…

Federated Learning (FL) is a widespread and well adopted paradigm of decentralized learning that allows training one model from multiple sources without the need to directly transfer data between participating clients. Since its inception…

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…

Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel…

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated…

One-shot federated learning (OSFL) reduces the communication cost and privacy risks of iterative federated learning by constructing a global model with a single round of communication. However, most existing methods struggle to achieve…

Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be learned efficiently using self-supervision, and they can…

Recently, label distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from labelel instances. Different from single-label and multi-label annotations, label distributions describe the instance…

Federated learning faces critical challenges in balancing communication efficiency and model accuracy. One key issue lies in the approximation of update errors without incurring high computational costs. In this paper, we propose a…

Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the remaining regions are irrelevant to the task at hand. Therefore,…

Generative based strategy has shown great potential in the Generalized Zero-Shot Learning task. However, it suffers severe generalization problem due to lacking of feature diversity for unseen classes to train a good classifier. In this…

Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of…

Fully-supervised crowd counting is a laborious task due to the large amounts of annotations. Few works focus on weekly-supervised crowd counting, where only the global crowd numbers are available for training. The main challenge of…

Federated Learning (FL) facilitates collaborative model training while prioritizing privacy by avoiding direct data sharing. However, most existing articles attempt to address challenges within the model's internal parameters and…

In this paper, we introduce Active Learning framework in Federated Learning for Target Domain Generalisation, harnessing the strength from both learning paradigms. Our framework, FEDALV, composed of Active Learning (AL) and Federated Domain…

A vision-language foundation model pretrained on very large-scale image-text paired data has the potential to provide generalizable knowledge representation for downstream visual recognition and detection tasks, especially on supplementing…

Deep learning-based fault diagnosis (FD) approaches require a large amount of training data, which are difficult to obtain since they are located across different entities. Federated learning (FL) enables multiple clients to collaboratively…

Federated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggregation fails due to conflicting optimization trajectories.…

Learning discriminative representations for subtle localized details plays a significant role in Fine-grained Visual Categorization (FGVC). Compared to previous attention-based works, our work does not explicitly define or localize the part…

Hierarchical Federated Learning (HFL) has recently emerged as a promising solution for intelligent decision-making in vehicular networks, helping to address challenges such as limited communication resources, high vehicle mobility, and data…