相关论文: One-to-Few Label Assignment for End-to-End Dense D…

In few-shot learning (FSL), the labeled samples are scarce. Thus, label errors can significantly reduce classification accuracy. Since label errors are inevitable in realistic learning tasks, improving the robustness of the model in the…

Reinforcement learning offers a promising approach for scan-order optimisation in laser additive manufacturing, where sequential scan decisions critically influence thermal accumulation, residual stress, distortion, and final part quality.…

Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with noisy labels, but such noise makes networks overfit seriously…

Various IoT applications demand resource-constrained machine learning mechanisms for different applications such as pervasive healthcare, activity monitoring, speech recognition, real-time computer vision, etc. This necessitates us to…

With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning rotated box (RBox) from the horizontal box (HBox) has attracted more and more attention. In this…

This paper presents a novel object detector called DEYOv2, an improved version of the first-generation DEYO (DETR with YOLO) model. DEYOv2, similar to its predecessor, DEYOv2 employs a progressive reasoning approach to accelerate model…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization,…

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Recently, an end-to-end two-dimensional sound source localization algorithm with ad-hoc microphone arrays formulates the sound source localization problem as a classification problem. The algorithm divides the target indoor space into a set…

In this paper we study \emph{many-to-one boundary labeling with backbone leaders}. In this new many-to-one model, a horizontal backbone reaches out of each label into the feature-enclosing rectangle. Feature points that need to be connected…

Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning using those selected…

Feature matching plays a fundamental role in many computer vision tasks, yet existing methods heavily rely on scarce and clean multi-view image collections, which constrains their generalization to diverse and challenging scenarios.…

Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced…

Memorization in over-parameterized neural networks could severely hurt generalization in the presence of mislabeled examples. However, mislabeled examples are hard to avoid in extremely large datasets collected with weak supervision. We…

In recent years, Discriminative Correlation Filter (DCF) based methods have significantly advanced the state-of-the-art in tracking. However, in the pursuit of ever increasing tracking performance, their characteristic speed and real-time…

We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset. Our framework considers…

Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Their performance is strictly connected with the quality of labels used in training. Unfortunately, acquiring good-quality…

We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our…

Entity recognition is a fundamental task in understanding document images. Traditional sequence labeling frameworks treat the entity types as class IDs and rely on extensive data and high-quality annotations to learn semantics which are…