Image Classification with AutoTrain

Fine-Tune ViT for Image Classification with 🤗 Transformers

Meta-Learning for Classifier Selection in Image Datasets: A Feature-Driven Framework for Accuracy Prediction

The paper introduces a meta‑learning framework that uses a rich set of dataset‑complexity meta‑features to predict the accuracy of different classifiers on image datasets, avoiding exhaustive training. By extracting features with autoencoders, pre‑trained networks, and dimensionality reduction, regression models estimate classifier accuracies, while clustering groups similar performers to simplify recommendations. Tested on 56 diverse image datasets, the method achieves over 86% ranking prediction accuracy, offering a scalable, interpretable solution for model selection and cost reduction.

Automated Background Swapping for Robustness against Spurious Backgrounds

arXiv:2606. 32018v1 Announce Type: cross Abstract: Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.

Mind the Tail: Data Selection Through Sparse Concepts

arXiv:2610.21007v1 Announce Type: new Abstract: Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocatio...

How to make effective use of domain experts for image classification?

arXiv:2609.17749v1 Announce Type: new Abstract: A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explo...

On the importance of multiple training seeds for evaluating machine unlearning

arXiv:2510. 26714v5 Announce Type: replace-cross Abstract: Machine unlearning aims to remove the influence of certain data points from a trained model without costly retraining.

TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset

arXiv:2608. 09091v1 Announce Type: cross Abstract: Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon massive datasets like ImageNet , CIFAR-100, or COCO .

Analyzing Visual Aircraft Representations with Sparse Autoencoders

arXiv:2606. 15468v1 Announce Type: cross Abstract: Vision models can achieve strong performance on classification tasks, but the internal representations supporting their predictions are often difficult to interpret.

Optimization as a Dynamical System: Generative Schedules from Latent ODEs

arXiv:2509. 23052v2 Announce Type: replace Abstract: We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent.

HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification

The paper introduces HAND, a biologically-inspired activation function that incorporates homeostasis, accelerating nonlinearity, and divisive normalization to act as an inductive bias in deep neural networks. Experiments on image classification show that using HAND allows a ConvNeXt-tiny model to reach ImageNet1k accuracy in 25 epochs versus 200 epochs for the baseline, and yields larger accuracy gains on long-tailed and reduced-data settings. The authors report that HAND does not degrade generalisation on common corruptions and can improve the model’s ability to reject unknown classes, with benefits observed across multiple CNN architectures and datasets.

Towards Interpretable Foundation Models for Retinal Fundus Images

arXiv:2603. 18846v3 Announce Type: replace-cross Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL).

An Ensemble-Based Self-Taught Learning Approach for Parking Space Classification Under Limited Data

The paper proposes an ensemble-based self‑taught learning framework for parking space classification that uses unsupervised convolutional autoencoders to learn transferable visual representations from unlabeled data. These learned encoders serve as fixed feature extractors for supervised classification with limited annotated samples, and an ensemble of heterogeneous autoencoders with independent classifier heads is employed to enhance robustness and reduce architectural bias. Experiments on PKLot and CNRPark benchmarks demonstrate that this approach significantly lowers annotation requirements while achieving high accuracies (93–96%) under cross‑dataset evaluation protocols.