Related papers: DSAM: A Distance Shrinking with Angular Marginaliz…
Overparametrized Deep Neural Networks (DNNs) often achieve astounding performances, but may potentially result in severe generalization error. Recently, the relation between the sharpness of the loss landscape and the generalization error…
Generating multiple new concepts remains a challenging problem in the text-to-image task. Current methods often overfit when trained on a small number of samples and struggle with attribute leakage, particularly for class-similar subjects…
The Segment Anything Model (SAM) exhibits strong zero-shot performance on natural images but suffers from domain shift and overconfidence when applied to medical volumes. We propose \textbf{CalSAM}, a lightweight adaptation framework that…
The visual appearance of a person is easily affected by many factors like pose variations, viewpoint changes and camera parameter differences. This makes person Re-Identification (ReID) among multiple cameras a very challenging task. This…
It is commonly believed that gradient compression in federated learning (FL) enjoys significant improvement in communication efficiency with negligible performance degradation. In this paper, we find that gradient compression induces…
In order to resist the adverse effect of viewpoint variations for improving vehicle re-identification performance, we design quadruple directional deep learning networks to extract quadruple directional deep learning features (QD-DLF) of…
We propose a novel object-augmented RGB-D SLAM system that is capable of constructing a consistent object map and performing relocalisation based on centroids of objects in the map. The approach aims to overcome the view dependence of…
Visible-infrared person re-identification (VI-ReID) aims to match specific pedestrian images from different modalities. Although suffering an extra modality discrepancy, existing methods still follow the softmax loss training paradigm,…
A central goal in deep learning is to learn compact representations of features at every layer of a neural network, which is useful for both unsupervised representation learning and structured network pruning. While there is a growing body…
Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of…
Detecting fraudulent auto-insurance claims remains a challenging classification problem, largely due to the extreme imbalance between legitimate and fraudulent cases. Standard learning algorithms tend to overfit to the majority class,…
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…
Deep AUC Maximization (DAM) is a new paradigm for learning a deep neural network by maximizing the AUC score of the model on a dataset. Most previous works of AUC maximization focus on the perspective of optimization by designing efficient…
Radars and cameras are mature, cost-effective, and robust sensors and have been widely used in the perception stack of mass-produced autonomous driving systems. Due to their complementary properties, outputs from radar detection (radar…
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the…
Autonomous vehicles demand detailed maps to maneuver reliably through traffic, which need to be kept up-to-date to ensure a safe operation. A promising way to adapt the maps to the ever-changing road-network is to use crowd-sourced data…
Person Re-identification (Person ReID) is an important topic in intelligent surveillance and computer vision. It aims to accurately measure visual similarities between person images for determining whether two images correspond to the same…
In recent years, the research community has approached the problem of vehicle re-identification (re-id) with attention-based models, specifically focusing on regions of a vehicle containing discriminative information. These re-id methods…
Object re-identification (ReID) is committed to searching for objects of the same identity across cameras, and its real-world deployment is gradually increasing. Current ReID methods assume that the deployed system follows the centralized…
Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor. However, the spatial context between these parts is ignored for the independent extractor…