Related papers: Efficient Detection of Bad Benchmark Items with No…
Amodal perception, the ability to comprehend complete object structures from partial visibility, is a fundamental skill, even for infants. Its significance extends to applications like autonomous driving, where a clear understanding of…
This work considers the problem of binary classification: given training data $x_1, \dots, x_n$ from a certain population, together with associated labels $y_1,\dots, y_n \in \left\{0,1 \right\}$, determine the best label for an element $x$…
Randomized smoothing has achieved great success for certified robustness against adversarial perturbations. Given any arbitrary classifier, randomized smoothing can guarantee the classifier's prediction over the perturbed input with…
Focusing on the most significant features of a dataset is useful both in machine learning (ML) and data mining. In ML, it can lead to a higher accuracy, a faster learning process, and ultimately a simpler and more understandable model. In…
Given a multivariate big time series, can we detect anomalies as soon as they occur? Many existing works detect anomalies by learning how much a time series deviates away from what it should be in the reconstruction framework. However, most…
Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but…
Benchmarks offer a scientific way to compare algorithms using objective performance metrics. Good benchmarks have two features: (a) they should be widely useful for many research groups; (b) and they should produce reproducible findings. In…
Topic models are typically evaluated with respect to the global topic distributions that they generate, using metrics such as coherence, but without regard to local (token-level) topic assignments. Token-level assignments are important for…
This work is concerned with the estimation of multidimensional regression and the asymptotic behaviour of the test involved in selecting models. The main problem with such models is that we need to know the covariance matrix of the noise to…
With the rapid advancement of generative AI, synthetic content across images, videos, and audio has become increasingly realistic, amplifying the risk of misinformation. Existing detection approaches predominantly focus on binary…
Adversarial examples, generated by carefully crafted perturbation, have attracted considerable attention in research fields. Recent works have argued that the existence of the robust and non-robust features is a primary cause of the…
RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…
While statement autoformalization has advanced rapidly, full-theorem autoformalization remains largely unexplored. Existing iterative refinement methods in statement autoformalization typically improve isolated aspects of formalization,…
We introduce a novel, practically relevant variation of the anomaly detection problem in multi-variate time series: intrinsic anomaly detection. It appears in diverse practical scenarios ranging from DevOps to IoT, where we want to…
The large language models (LLMs) are able to generate high-quality texts in multiple languages. Such texts are often not recognizable by humans as generated, and therefore present a potential of LLMs for misuse (e.g., plagiarism, spams,…
This study introduces a novel nonparametric approach for detecting Differential Item Functioning (DIF) in binary items through direct comparison of Item Response Curves (IRCs). Building on prior work on nonparametric comparison of…
Precise detection of tiny objects in remote sensing imagery remains a significant challenge due to their limited visual information and frequent occurrence within scenes. This challenge is further exacerbated by the practical burden and…
Suppose $L$ simultaneous independent stochastic systems generate observations, where the observations from each system depend on the underlying parameter of that system. The observations are unlabeled (anonymized), in the sense that an…
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising. Analysis of fairness in real-world vision systems, such as…
Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…