English
Related papers

Related papers: Trade-offs in Top-k Classification Accuracies on L…

200 papers

Recommender systems (RS) aim to retrieve a small set of items that best match individual user preferences. Naturally, RS place primary emphasis on the quality of the Top-$K$ results rather than performance across the entire item set.…

Information Retrieval · Computer Science 2026-01-28 Shengjia Zhang , Weiqin Yang , Jiawei Chen , Peng Wu , Yuegang Sun , Gang Wang , Qihao Shi , Can Wang

A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…

Artificial Intelligence · Computer Science 2026-03-12 Tung Tran , Danilo Vasconcellos Vargas , Khoat Than

The bias-variance trade-off is a central concept in supervised learning. In classical statistics, increasing the complexity of a model (e.g., number of parameters) reduces bias but also increases variance. Until recently, it was commonly…

Machine Learning · Statistics 2022-03-25 Jason W. Rocks , Pankaj Mehta

Deep Neural Networks (DNNs) have achieved remarkable success in a variety of tasks, especially when it comes to prediction accuracy. However, in complex real-world scenarios, particularly in safety-critical applications, high accuracy alone…

Artificial Intelligence · Computer Science 2024-05-31 Han Liu , Peng Cui , Bingning Wang , Jun Zhu , Xiaolin Hu

Average-K classification is an alternative to top-K classification in which the number of labels returned varies with the ambiguity of the input image but must average to K over all the samples. A simple method to solve this task is to…

Machine Learning · Computer Science 2023-04-03 Camille Garcin , Maximilien Servajean , Alexis Joly , Joseph Salmon

We propose a simple modification from a fixed margin triplet loss to an adaptive margin triplet loss. While the original triplet loss is used widely in classification problems such as face recognition, face re-identification and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-14 Mai Lan Ha , Volker Blanz

Training autoregressive models to better predict under the test metric, instead of maximizing the likelihood, has been reported to be beneficial in several use cases but brings additional complications, which prevent wider adoption. In this…

Machine Learning · Computer Science 2019-12-10 Irina Saparina , Anton Osokin

The inability to guarantee robustness is one of the major obstacles to the application of deep learning models in security-demanding domains. We identify that the most commonly used cross-entropy (CE) loss does not guarantee robust boundary…

Machine Learning · Computer Science 2023-02-21 Weiwei Gao , Dazhi Zhang , Yao Li , Zhichang Guo , Ovanes Petrosian

Assessing disease severity with ordinal classes, where each class reflects increasing severity levels, benefits from loss functions designed for this ordinal structure. Traditional categorical loss functions, like Cross-Entropy (CE), often…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Gorkem Polat , Ümit Mert Çağlar , Alptekin Temizel

Classification performance is often not uniform over the data. Some areas in the input space are easier to classify than others. Features that hold information about the "difficulty" of the data may be non-discriminative and are therefore…

Machine Learning · Computer Science 2016-05-24 Oran Richman , Shie Mannor

Loss functions play a central role in supervised classification. Cross-entropy (CE) is widely used, whereas the mean absolute error (MAE) loss can offer robustness but is difficult to optimize. Interpolating between the CE and MAE losses,…

Machine Learning · Statistics 2026-04-29 Kartheek Bondugula , Santiago Mazuelas , Aritz Pérez , Anqi Liu

Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning using those selected…

Machine Learning · Computer Science 2026-01-09 Shogo Nakayama , Masahiro Okuda

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

Machine Learning · Computer Science 2022-12-27 Justin Leo , Jugal Kalita

Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many different models and then aggregate their predictions. This is…

Computer Vision and Pattern Recognition · Computer Science 2022-12-15 Le Zhang , Qibin Hou , Yun Liu , Jia-Wang Bian , Xun Xu , Joey Tianyi Zhou , Ce Zhu

Pairwise ranking methods are the basis of many widely used discriminative training approaches for structure prediction problems in natural language processing(NLP). Decomposing the problem of ranking hypotheses into pairwise comparisons…

Computation and Language · Computer Science 2017-07-19 Huadong Chen , Shujian Huang , David Chiang , Xinyu Dai , Jiajun Chen

Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance. Inspired by the recently introduced…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Attila Szabo , Hadi Jamali-Rad , Siva-Datta Mannava

We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding a multi-scale topological loss term. Disentanglement is a crucial property of data representations substantial for the…

Machine Learning · Computer Science 2025-03-17 Nikita Balabin , Daria Voronkova , Ilya Trofimov , Evgeny Burnaev , Serguei Barannikov

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao

We suggest a loss for learning deep embeddings. The new loss does not introduce parameters that need to be tuned and results in very good embeddings across a range of datasets and problems. The loss is computed by estimating two…

Computer Vision and Pattern Recognition · Computer Science 2016-11-04 Evgeniya Ustinova , Victor Lempitsky

Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Correlation of Loss Differences (CLD), a simple and…

Machine Learning · Computer Science 2025-11-20 Manish Nagaraj , Deepak Ravikumar , Kaushik Roy