SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 22512275 of 10420 papers

TitleStatusHype
Convolution-enhanced Evolving Attention NetworksCode1
A graph-transformer for whole slide image classificationCode1
A synergistic CNN-transformer network with pooling attention fusion for hyperspectral image classificationCode1
ML-Decoder: Scalable and Versatile Classification HeadCode1
DeiT III: Revenge of the ViTCode1
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision ModelsCode1
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision TransformersCode1
PairAug: What Can Augmented Image-Text Pairs Do for Radiology?Code1
Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic SegmentationCode1
A self-interpretable module for deep image classification on small dataCode0
Invariant Shape Representation Learning For Image ClassificationCode0
Invariance encoding in sliced-Wasserstein space for image classification with limited training dataCode0
A second-order-like optimizer with adaptive gradient scaling for deep learningCode0
A Group-Theoretic Framework for Data AugmentationCode0
Compressing Vision Transformers for Low-Resource Visual LearningCode0
Invariant backpropagation: how to train a transformation-invariant neural networkCode0
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation ModelCode0
A Scalable Quantum Non-local Neural Network for Image ClassificationCode0
Compressing Deep CNNs using Basis Representation and Spectral Fine-tuningCode0
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual ClassificationCode0
Compress image to patches for Vision TransformerCode0
Interpretable Network Visualizations: A Human-in-the-Loop Approach for Post-hoc Explainability of CNN-based Image ClassificationCode0
Compressed learning based onboard semantic compression for remote sensing platformsCode0
Compressed Learning: A Deep Neural Network ApproachCode0
Intra-class Patch Swap for Self-DistillationCode0
Show:102550
← PrevPage 91 of 417Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified