Related papers: Error-Decomposed Class-Conditional Fusion for Stat…
Clustered federated learning (CFL) addresses the performance challenges posed by data heterogeneity in federated learning (FL) by organizing edge devices with similar data distributions into clusters, enabling collaborative model training…
Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…
High energy density physics (HEDP) experiments commonly involve a dynamic wave-front propagating inside a low-density foam. This effect affects its density and hence, its transparency. A common problem in foam production is the creation of…
Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…
Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…
Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings,…
Recent advancements in object detection rely on modular architectures with multi-scale fusion and attention mechanisms. However, static fusion heuristics and class-agnostic attention limit performance in dynamic scenes with occlusions,…
A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typically k-means, to produce pseudo-labels that guide training,…
This study addresses critical industrial challenges in e-commerce product categorization, namely platform heterogeneity and the structural limitations of existing taxonomies, by developing and deploying a multimodal hierarchical…
Entropy Minimization (EM) is beneficial to reducing class overlap, bridging domain gap, and restricting uncertainty for various tasks in machine learning, yet its potential is limited. To study the internal mechanism of EM, we reformulate…
Accurate estimation of the Worst-Case Deadline Failure Probability (WCDFP) has attracted growing attention as a means to provide safety assurances in complex systems such as robotic platforms and autonomous vehicles. WCDFP quantifies the…
Major data protection regulations all mention the "right to be forgotten," and that's what pushed federated unlearning (FU) techniques forward. But one stubborn issue remains: catastrophic forgetting--you erase the target knowledge, yet…
Reliable uncertainty quantification is critical for trustworthy AI. Conformal Prediction (CP) provides prediction sets with distribution-free coverage guarantees, but its two main variants face complementary limitations. Split CP (SCP)…
Quantifying the data uncertainty in learning tasks is often done by learning a prediction interval or prediction set of the label given the input. Two commonly desired properties for learned prediction sets are \emph{valid coverage} and…
Deploying continual object detection on microcontrollers (MCUs) with under 100KB memory requires efficient feature compression that can adapt to evolving task distributions. Existing approaches rely on fixed compression strategies (e.g.,…
Exemplar-free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in…
Object detection in camera images, using deep learning has been proven successfully in recent years. Rising detection rates and computationally efficient network structures are pushing this technique towards application in production…
Security issues in shipped code can lead to unforeseen device malfunction, system crashes or malicious exploitation by crackers, post-deployment. These vulnerabilities incur a cost of repair and foremost risk the credibility of the company.…
Conventional object detectors typically operate under a closed-set assumption, limiting recognition to a predefined set of base classes seen during training. Open-vocabulary object detection (OVD) addresses this limitation by leveraging…
With the widespread application of personalized online services, click-through rate (CTR) prediction has received more and more attention and research. The most prominent features of CTR prediction are its multi-field categorical data…