Related papers: Robust and Label-Efficient Deep Waste Detection

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main reasons for which is the limited training data.…

Software vulnerabilities (SVs) have become a common, serious, and crucial concern to safety-critical security systems. That leads to significant progress in the use of AI-based methods for software vulnerability detection (SVD). In…

How can models effectively detect out-of-distribution (OOD) samples in complex, multi-label settings without extensive retraining? Existing OOD detection methods struggle to capture the intricate semantic relationships and label…

Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly…

Developing robot perception systems for recognizing objects in the real-world requires computer vision algorithms to be carefully scrutinized with respect to the expected operating domain. This demands large quantities of ground truth data…

Mobile robots and autonomous vehicles rely on multi-modal sensor setups to perceive and understand their surroundings. Aside from cameras, LiDAR sensors represent a central component of state-of-the-art perception systems. In addition to…

Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many…

Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on image classification tasks and neglected object detection…

Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to achieve a trade-off between labeling burden and performance,…

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out…

Deep approaches to anomaly detection have recently shown promising results over shallow methods on large and complex datasets. Typically anomaly detection is treated as an unsupervised learning problem. In practice however, one may…

Accurate waste classification is vital for achieving sustainable waste management and reducing the environmental footprint of urbanization. Misclassification of recyclable materials contributes to landfill accumulation, inefficient…

Machine learning classification systems are susceptible to poor performance when trained with incorrect ground truth labels, even when data is well-curated by expert annotators. As machine learning becomes more widespread, it is…

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the…

Open-set semi-supervised learning (OSSL) has attracted growing interest, which investigates a more practical scenario where out-of-distribution (OOD) samples are only contained in unlabeled data. Existing OSSL methods like OpenMatch learn…

Accurate waste disposal, at the point of disposal, is crucial to fighting climate change. When materials that could be recycled or composted get diverted into landfills, they cause the emission of potent greenhouse gases such as methane.…

Self-supervised learning systems have gained significant attention in recent years by leveraging clustering-based pseudo-labels to provide supervision without the need for human annotations. However, the noise in these pseudo-labels caused…

Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…

I present the Lower Biased Teacher model, an enhancement of the Unbiased Teacher model, specifically tailored for semi-supervised object detection tasks. The primary innovation of this model is the integration of a localization loss into…