Related papers: Machine Learning-Based Cluster Classification to S…

In recent years, the background-aware correlation filters have achie-ved a lot of research interest in the visual target tracking. However, these methods cannot suitably model the target appearance due to the exploitation of hand-crafted…

Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data augmentation schemes; and collecting more labeled data. We…

The Multi-gap Resistive Plate Chamber (MRPC) is an advanced form of Resistive Plate Chamber (RPC) detector where the gas gap is divided into sub-gaps. MRPCs are known for their good time resolution and detection efficiency for charged…

This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this…

The labeling cost of large number of bounding boxes is one of the main challenges for training modern object detectors. To reduce the dependence on expensive bounding box annotations, we propose a new semi-supervised object detection…

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Accurate quantum state readout is crucial for error correction and algorithms, but measurement errors are detrimental. Readout fidelity is typically limited by a poor signal-to-noise ratio (SNR) and energy relaxation ($T_1$ decay), a…

Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that…

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels that include both the true label and irrelevant noise labels. In this paper, we propose a novel multi-level generative…

Recent deep clustering models have produced impressive clustering performance. However, a common issue with existing methods is the disparity between global and local feature structures. While local structures typically show strong…

Deep Learning has demonstrated a significant improvement against traditional machine learning approaches in different domains such as image and speech recognition. Their success on benchmark datasets is transferred to the real-world through…

Semi-supervised segmentation methods have demonstrated promising results in natural scenarios, providing a solution to reduce dependency on manual annotation. However, these methods face significant challenges when directly applied to…

Unsupervised person re-identification (Re-ID) aims to learn a feature network with cross-camera retrieval capability in unlabelled datasets. Although the pseudo-label based methods have achieved great progress in Re-ID, their performance in…

Self-supervised heterogeneous graph learning (SHGL) has shown promising potential in diverse scenarios. However, while existing SHGL methods share a similar essential with clustering approaches, they encounter two significant limitations:…

Particle identification at the Super Charm-Tau factory experiment will be provided by a Focusing Aerogel Ring Imaging CHerenkov detector (FARICH). The specifics of detector location make proper cooling difficult, therefore a significant…

Small moving target detection is crucial for many defense applications but remains highly challenging due to low signal-to-noise ratios, ambiguous visual cues, and cluttered backgrounds. In this work, we propose a novel deep learning…

The use of machine learning algorithms is an attractive way to produce very fast detector simulations for scattering reactions that can otherwise be computationally expensive. Here we develop a factorised approach where we deal with each…

We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds. We create a toolkit for disentangling foreground and background signal on ImageNet images, and find that (a) models can…

Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training…