相关论文: Community-aware evaluation and threshold calibrati…

Reliable and accurate estimation of the error of an ML model in unseen test domains is an important problem for safe intelligent systems. Prior work uses disagreement discrepancy (DIS^2) to derive practical error bounds under distribution…

Given a sufficiently large training dataset, it is relatively easy to train a modern convolution neural network (CNN) as a required image classifier. However, for the task of fish classification and/or fish detection, if a CNN was trained…

Static benchmarks measure a model frozen at training time. Real systems face distribution shift: new categories, paraphrased queries, drift: and must recover online via user corrections. No existing benchmark measures recovery speed under…

The Artificial Benchmark for Community Detection (ABCD) graph is a random graph model with community structure and power-law distribution for both degrees and community sizes. The model generates graphs similar to the well-known LFR model…

As human activities intensify, environmental systems such as aquatic ecosystems and water treatment systems face increasingly complex pressures, impacting ecological balance, public health, and sustainable development, making intelligent…

In some scenarios, classifier requires detecting out-of-distribution samples far from its training data. With desirable characteristics, reconstruction autoencoder-based methods deal with this problem by using input reconstruction error as…

Open-world object detection (OWOD) requires detectors to localize known classes while identifying unknown objects for future incremental learning. We find that the unknown prediction streams of strong OWOD detectors are heavily polluted: on…

Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image…

Autonomous navigation in crowded spaces poses a challenge for mobile robots due to the highly dynamic, partially observable environment. Occlusions are highly prevalent in such settings due to a limited sensor field of view and obstructing…

Recent research underscores the pivotal role of the Out-of-Distribution (OOD) feature representation field scale in determining the efficacy of models in OOD detection. Consequently, the adoption of model ensembles has emerged as a…

The primary assumption of conventional supervised learning or classification is that the test samples are drawn from the same distribution as the training samples, which is called closed set learning or classification. In many practical…

Existing open-set recognition (OSR) studies typically assume that each image contains only one class label, with the unknown test set (negative) having a disjoint label space from the known test set (positive), a scenario referred to as…

Marine visual understanding is essential for monitoring and protecting marine ecosystems, enabling automatic and scalable biological surveys. However, progress is hindered by limited training data and the lack of a systematic task…

Underwater surveys provide long-term data for informing management strategies, monitoring coral reef health, and estimating blue carbon stocks. Advances in broad-scale survey methods, such as robotic underwater vehicles, have increased the…

Remote sensing change detection plays a pivotal role in domains such as environmental monitoring, urban planning, and disaster assessment. However, existing methods typically rely on predefined categories and large-scale pixel-level…

Given the increasing complexity of omics datasets, a key challenge is not only improving classification performance but also enhancing the transparency and reliability of model decisions. Effective model performance and feature selection…

Open-world object detection (OWOD), as a more general and challenging goal, requires the model trained from data on known objects to detect both known and unknown objects and incrementally learn to identify these unknown objects. The…

Animal pose estimation has become a crucial area of research, but the scarcity of annotated data is a significant challenge in developing accurate models. Synthetic data has emerged as a promising alternative, but it frequently exhibits…

Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature. However, the field currently lacks a unified,…