Related papers: Utilizing the Mean Teacher with Supcontrast Loss f…

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage…

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate…

With the progress of Mars exploration, numerous Mars image data are collected and need to be analyzed. However, due to the imbalance and distortion of Martian data, the performance of existing computer vision models is unsatisfactory. In…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

We introduce a powerful student-teacher framework for the challenging problem of unsupervised anomaly detection and pixel-precise anomaly segmentation in high-resolution images. Student networks are trained to regress the output of a…

We introduce Integrated Weak Learning, a principled framework that integrates weak supervision into the training process of machine learning models. Our approach jointly trains the end-model and a label model that aggregates multiple…

Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…

Weakly-supervised image segmentation (WSIS) is a critical task in computer vision that relies on image-level class labels. Multi-stage training procedures have been widely used in existing WSIS approaches to obtain high-quality pseudo-masks…

Automatic defect detection for 3D printing processes, which shares many characteristics with change detection problems, is a vital step for quality control of 3D printed products. However, there are some critical challenges in the current…

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present…

Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap between classification and segmentation still hampers the model to…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

Defect detection is a critical research area in artificial intelligence. Recently, synthetic data-based self-supervised learning has shown great potential on this task. Although many sophisticated synthesizing strategies exist, little…

The increasing intensity and frequency of floods is one of the many consequences of our changing climate. In this work, we explore ML techniques that improve the flood detection module of an operational early flood warning system. Our…

In Multiple Instance learning (MIL), weak labels are provided at the bag level with only presence/absence information known. However, there is a considerable gap in performance in comparison to a fully supervised model, limiting the…

With the escalated demand of human-machine interfaces for intelligent systems, development of gaze controlled system have become a necessity. Gaze, being the non-intrusive form of human interaction, is one of the best suited approach.…

Lens flare removal is challenging due to the large spatial extent of flare artifacts and their entanglement with scene structures, while existing methods heavily rely on large-scale paired data. We propose a semi-supervised flare removal…

We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a memory-based method trained on an unlabeled data stream, where…

Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1)…

Radio Frequency (RF) device fingerprinting has been recognized as a potential technology for enabling automated wireless device identification and classification. However, it faces a key challenge due to the domain shift that could arise…