English
Related papers

Related papers: Classification with Conceptual Safeguards

200 papers

We introduce a framework for calibrating machine learning models so that their predictions satisfy explicit, finite-sample statistical guarantees. Our calibration algorithms work with any underlying model and (unknown) data-generating…

Machine Learning · Computer Science 2022-10-03 Anastasios N. Angelopoulos , Stephen Bates , Emmanuel J. Candès , Michael I. Jordan , Lihua Lei

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…

Machine Learning · Computer Science 2023-11-09 Jinyung Hong , Keun Hee Park , Theodore P. Pavlic

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…

Computer Vision and Pattern Recognition · Computer Science 2016-11-29 Klaus Greff , Antti Rasmus , Mathias Berglund , Tele Hotloo Hao , Jürgen Schmidhuber , Harri Valpola

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Schrasing Tong , Antoine Salaun , Vincent Yuan , Annabel Adeyeri , Lalana Kagal

Conformal prediction has recently emerged as a promising strategy for quantifying the uncertainty of a predictive model; these algorithms modify the model to output sets of labels that are guaranteed to contain the true label with high…

Machine Learning · Computer Science 2025-03-11 Botong Zhang , Shuo Li , Osbert Bastani

Conformal prediction is a statistically rigorous method for quantifying uncertainty in models by having them output sets of predictions, with larger sets indicating more uncertainty. However, prediction sets are not inherently actionable;…

Machine Learning · Computer Science 2025-02-17 Jesse C. Cresswell , Bhargava Kumar , Yi Sui , Mouloud Belbahri

We propose a multi-scale extension of conformal prediction, an approach that constructs prediction sets with finite-sample coverage guarantees under minimal statistical assumptions. Classic conformal prediction relies on a single notion of…

Statistics Theory · Mathematics 2025-02-11 Ali Baheri , Marzieh Amiri Shahbazi

Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as…

Machine Learning · Computer Science 2026-04-29 Chandler Squires , Pradeep Ravikumar

The modern pervasiveness of large-scale deep neural networks (NNs) is driven by their extraordinary performance on complex problems but is also plagued by their sudden, unexpected, and often catastrophic failures, particularly on…

Machine Learning · Computer Science 2023-08-02 Sadhana Lolla , Iaroslav Elistratov , Alejandro Perez , Elaheh Ahmadi , Daniela Rus , Alexander Amini

It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a…

Computer Vision and Pattern Recognition · Computer Science 2022-12-01 Zhengcong Fei , Mingyuan Fan , Li Zhu , Junshi Huang , Xiaoming Wei , Xiaolin Wei

Humans can learn and reason under substantial uncertainty in a space of infinitely many concepts, including structured relational concepts ("a scene with objects that have the same color") and ad-hoc categories defined through goals…

Artificial Intelligence · Computer Science 2020-10-07 Ramakrishna Vedantam , Arthur Szlam , Maximilian Nickel , Ari Morcos , Brenden Lake

Deep learning models have demonstrated remarkable capabilities in learning complex patterns and concepts from training data. However, recent findings indicate that these models tend to rely heavily on simple and easily discernible features…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Raha Ahmadi , Mohammad Javad Rajabi , Mohammad Khalooie , Mohammad Sabokrou

Knowing when a classifier's prediction can be trusted is useful in many applications and critical for safely using AI. While the bulk of the effort in machine learning research has been towards improving classifier performance,…

Machine Learning · Statistics 2018-10-30 Heinrich Jiang , Been Kim , Melody Y. Guan , Maya Gupta

While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree. Uncertainty methods are designed to provide…

Machine Learning · Statistics 2020-06-17 Adam M. Oberman , Chris Finlay , Alexander Iannantuono , Tiago Salvador

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples…

Computer Vision and Pattern Recognition · Computer Science 2016-07-20 Xiaojie Jin , Yunpeng Chen , Jian Dong , Jiashi Feng , Shuicheng Yan

Concept induction requires the extraction and naming of concepts from noisy perceptual experience. For supervised approaches, as the number of concepts grows, so does the number of required training examples. Philosophers, psychologists,…

Machine Learning · Computer Science 2020-01-20 Brett D. Roads , Bradley C. Love

Reliable uncertainty quantification is critical in high-stakes applications, such as medical diagnosis, where confidently incorrect predictions can erode trust in automated decision-making systems. Traditional uncertainty quantification…

Image and Video Processing · Electrical Eng. & Systems 2025-10-21 Hassan Gharoun , Mohammad Sadegh Khorshidi , Fang Chen , Amir H. Gandomi

In this paper, we introduce a selective zero-shot classification problem: how can the classifier avoid making dubious predictions? Existing attribute-based zero-shot classification methods are shown to work poorly in the selective…

Computer Vision and Pattern Recognition · Computer Science 2018-07-20 Jie Song , Chengchao Shen , Jie Lei , An-Xiang Zeng , Kairi Ou , Dacheng Tao , Mingli Song

We propose a new method for conducting Bayesian prediction that delivers accurate predictions without correctly specifying the unknown true data generating process. A prior is defined over a class of plausible predictive models. After…

Methodology · Statistics 2020-08-24 Ruben Loaiza-Maya , Gael M. Martin , David T. Frazier

Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and…

Computer Vision and Pattern Recognition · Computer Science 2023-02-07 Fabian Küppers