General Classification
3932 papers with code • 11 benchmarks • 8 datasets
Algorithms trying to solve the general task of classification.
Benchmarks
These leaderboards are used to track progress in General Classification
Libraries
Use these libraries to find General Classification models and implementationsLatest papers
A Data-Efficient Deep Learning Framework for Segmentation and Classification of Histopathology Images
The current study of cell architecture of inflammation in histopathology images commonly performed for diagnosis and research purposes excludes a lot of information available on the biopsy slide.
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods.
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network
However, training them requires substantial accelerator memory for saving large, multi-resolution activations.
Protoformer: Embedding Prototypes for Transformers
This paper proposes Protoformer, a novel self-learning framework for Transformers that can leverage problematic samples for text classification.
Truly Unordered Probabilistic Rule Sets for Multi-class Classification
Still, existing methods have several shortcomings: 1) most recent methods require a binary feature matrix as input, while learning rules directly from numeric variables is understudied; 2) existing methods impose orders among rules, either explicitly or implicitly, which harms interpretability; and 3) currently no method exists for learning probabilistic rule sets for multi-class target variables (there is only one for probabilistic rule lists).
Differentiable Top-k Classification Learning
In this work, we relax this assumption and optimize the model for multiple k simultaneously instead of using a single k. Leveraging recent advances in differentiable sorting and ranking, we propose a differentiable top-k cross-entropy classification loss.
LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks
LIFT does not make any changes to the model architecture or loss function, and it solely relies on the natural language interface, enabling "no-code machine learning with LMs."
Evaluating histopathology transfer learning with ChampKit
Histopathology remains the gold standard for diagnosis of various cancers.
Localizing Semantic Patches for Accelerating Image Classification
This ensures the exact mapping from a high-level spatial location to the specific input image patch.
Hopular: Modern Hopfield Networks for Tabular Data
In experiments on small-sized tabular datasets with less than 1, 000 samples, Hopular surpasses Gradient Boosting, Random Forests, SVMs, and in particular several Deep Learning methods.