Classification

Follow this topic Ask about this topic

Momentum

45 papers in the last four weeks, up 137% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 254

All topics

A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification
Aug 14, 2026Christiaan M. Geldenhuys, Thomas R. NieslerFew-Shot Audio Classification Prototype-Based Classification
Department of Electrical and Electronic Engineering University of Stellenbosch
Bagging Robustly Learns VC Classes with Linear Sample Complexity
Aug 13, 2026Omar MontasserAdversarial Robustness Classification
Yale University
When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers
Aug 12, 2026Yang Liu, Ran ZouLLM Backdoor Attacks Backdoor Detection
Department of Statistics and Operations Research, University of North Carolina at Chapel Hill · Department of Statistics, University of California, Irvine
Robust and Efficient Noisy-Label Time-Series Classification via Dynamic Time Warping Based Granular Ball Computing
Aug 12, 2026Ziqiang Li, Yun Liu, Gouhei TanakaDynamic Time Warping Time Series Classification
Department of Computer Science, Graduate School of Engineering, Nagoya Institute of Technology, Nagoya, 466-8555, Japan · International Research Center for Neurointelligence, The University of Tokyo, Tokyo, 113-0033, Japan. · Faculty of Information and Human Sciences, Kyoto Institute of Technology, Kyoto, 606-8585, Japan
CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classification
Aug 11, 2026Gawon LimLong-Tailed Classification Ensemble Learning
School of Information Sciences University of Illinois Urbana-Champaign
Optimistic Rates for Multiclass PAC Learning
Aug 11, 2026Xiaoyu Li, Andi Han, Jiaojiao Jiang +1Multiclass Classification Classification
University of New South Wales · University of Sydney
MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection
Aug 11, 2026Jinmo Han, Jimin Hong, Chanyeong Moon +3AI-Generated Text Detection Prototype Learning
Department of Electrical and Computer Engineering and INMC Seoul National University, Seoul, Republic of Korea
ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning
Aug 10, 2026Ange-Clément Akazan, Ineza Remy Mugenga, Abebe Geletu +2Chance-Constrained Optimization Classification
School of Agriculture and Science, University of KwaZulu-Natal, Pietermaritzburg, KwaZulu-Natal, South Africa · 2AIMS Research and Innovation Centre, African Institute for Mathematical Sciences, Kigali, Rwanda · 3African Institute for Mathematical Sciences, Kigali, Rwanda
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Aug 10, 2026Chidaksh Ravuru, Shashank SrivastavaClassification Spurious Correlation Robustness
Department of Computer Science University of North Carolina, Chapel Hill
Are LLMs Positionally Consistent Ordinal Classifiers? A Systematic Evaluation
Aug 9, 2026Yu Wang, Zhe Zhou, Menglin Liu +1Language Model Bias Evaluation Classification
Cornell University · University of Washington · The Chinese University of Hong Kong, Shenzhen +1
Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
Aug 6, 2026Alex Buna, Shirley Xiaoqi Liu, Patrick RebeschiniEarly Stopping Gradient Descent
Department of Statistics, University of Oxford
Evidential Rule Learning for Interpretable Classification with Abstention
Aug 6, 2026Javier Fumanal-Idocin, Javier Andreu-PerezSelective Prediction Interpretable ML
School of Computer Science and Electronic Engineering University of Essex, Colchester CO4 3SQ, UK
Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples
Aug 5, 2026Nilesh KumarTraining Data Selection Classification
SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
Aug 4, 2026Boyao Wang, Zhihan LeiParameter-Free Mixture-of-Experts Routing Adaptive Model Routing
Machine Learning Department Carnegie Mellon University
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
Aug 3, 2026Nan Chen, Zhouhao Yang, Soufiane HayouZero-Shot Learning LLM Evaluation
Department of Applied Mathematics and Statistics Johns Hopkins University
Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification
Aug 3, 2026Sajjad Abdoli, Ghassan Al-Sumaidaee, Ahmad ElShiekh +1Audio-Language Model Evaluation Audio-Language Models
Perle
BRiG-AFA: Bellman Risk-to-Go Learning for Non-Myopic Active Feature Acquisition
Aug 3, 2026Jiaorong Feng, Qian Li, Ying LiCost-Aware Inference Active Learning
Curtin Business School, Curtin University, Perth, Western Australia, Australia · †Present affiliation: Independent Researcher. · School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth, Western Australia, Australia
Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification
Aug 3, 2026Linzhuo Han, Zongyong Cui, Houbiao LiAutomatic Modulation Classification Classification
School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, China · School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
Statistical comparisons of time-series feature sets on classification tasks
Aug 3, 2026Trent Henderson, Ben D. FulcherTime Series Classification Classification
Dynamics and Neural Systems Lab, The University of Sydney, Camperdown, 2006, NSW, Australia.
Factorized AdaBoost.MH Achieves the Same Convergence Rate as AdaBoost.MH
Aug 2, 2026Xin Zou, Jingyuan XuEnsemble Learning Multiclass Classification
Subtype Robustness Is Not Just Accuracy: Calibration Under Unseen Subtype Shift
Aug 2, 2026Hanyu Su, Carlota Julbe i Juanola, Yibo HuDistribution Shift Robustness Neural Network Robustness
Illinois Institute of Technology
Loanword or Switch? The Annotation Boundary, Not the Model, Drives Kazakh-Russian Code-Switching Identification
Aug 1, 2026Bogdan SavelyevCode-Switching Language Identification
Independent Researcher Kazakhstan
FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models
Jul 31, 2026Jeffrey M. Girard, Jason Z. Zheng, Jacqueline R. Vertino +2Classification Multimodal Model Evaluation
Fluid Concepts Research
Explaining AI-Image Detection: What the Heatmap Actually Shows
Jul 31, 2026Leonid Kuturin, Ilya Sotnikov, Mark Khusnutdinov +4Image Forgery Detection Digital Image Forensics
Sirius Educational Centre, Big Challenges programme · HSE University, Faculty of Computer Science
Search Strategies for Optimal Classification and Regression Trees
Jul 30, 2026Jacobus G. M. van der Linden, Mim van den Bos, Emir DemirovićDecision Tree Learning Classification
Delft University of Technology
Contrastive Concept Importance: Explaining Pairwise Class Decisions Through Automatically Extracted Concept Representations
Jul 30, 2026Roel Visser, Isaac Roberts, Barbara HammerFeature Attribution Pairwise Comparison
Bielefeld University, Inspiration 1, 33619 Bielefeld, Germany
Knowledge before Reasoning: EC-Reason-Bench, a Training-Free Diagnostic Benchmark for LLM Enzyme Classification
Jul 29, 2026Linyu Li, Zhi Jin, Yichi Zhang +6Retrieval-Augmented Generation LLM Evaluation
School of Computer Science, Peking University, Beijing, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China · School of Computer Science, Tibet University, Lhasa, China
FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery
Jul 28, 2026Reihaneh Rostami, Brian GoodwinActive Learning Classification
RAIC Labs · RAIC Labs USA
Multiclass Classification without Labels via Posterior Simplex Geometry
Jul 27, 2026Raphaël Bonnet-Guerrini, Johann Ioannou-Nikolaides, Troels Petersen +1Multiclass Classification Weakly Supervised Learning
Niels Bohr Institute University of Copenhagen Copenhagen, 2100 · Computer Science Department Università degli Studi di Milano Milan, MI, 20133
A Model for Imbalanced Label Aggregation: A Focus on Minority-Class Detection
Jul 27, 2026Gabriel Singer, Samuel Gruffaz, Olivier Vo Van +2Class-Imbalanced Learning Classification
SNCF, Paris, France · Université Paris-Saclay, ENS Paris-Saclay, Centre Borelli, France · 2Tampere University, Finland, Biostatistics group

Aug 14, 2026, eess.ASJ/K move · Enter open · S save

A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification

Christiaan M. Geldenhuys, Thomas R. Niesler

Department of Electrical and Electronic Engineering University of Stellenbosch

Few-Shot Audio Classification Prototype-Based Classification Classification Audio Classification

Open paper AskPDF arXiv

We present a parameter-free episodic evaluation of nearest-centroid classification of elephant vocalisations on fixed pretrained embeddings, for the Elephant Voices (EV) and Linguistic Data Consortium (LDC) datasets. We ask not which embedding yields the best classifier trained on all labelled data, but how the simplest classifier performs as the number of exemplars per class varies. There are no learnable parameters, because each class is modelled as the mean of its support embeddings and each query is assigned to the nearest centroid under squared Euclidean distance. Evaluation covers the fixed Perch (ver. 1), Perch (ver. 2) and HuBERT (base, layer 2) embeddings, alongside mel frequency cepstral coefficient (MFCC) features,

N

-way

k

-shot, under the same stratified

K

-fold cross-validation protocol as the trained classifiers. None of these embedding models was trained to distinguish elephant call types. On the smaller EV dataset the centroid classifier is markedly data-efficient. Using Perch (ver. 1) or Perch (ver. 2) embeddings it overtakes in mean average precision (mAP) the fully-trained logistic regression (LR) baseline from one or two exemplars and the recurrent baseline from two. Over the reduced set of call types on which the strongly-supervised end-to-end baseline was trained, the centroid classifier using Perch (ver. 2) embeddings overtakes that baseline in mAP as well, from two exemplars. On the larger LDC dataset the recurrent baselines retain their advantage for all considered values of

k

. Only LR is overtaken, and only in mAP. Nearest-centroid classification is therefore preferable precisely when exemplars are few and the fixed embedding already separates the call types.

Momentum

Related topics

Latest papers 254