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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1651–1700 of 10419 papers

TitleStatusHype
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
Dynamic Grained Encoder for Vision TransformersCode1
Dynamic Defense Against Byzantine Poisoning Attacks in Federated LearningCode1
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image ClassificationCode1
Dynamic Graph Message Passing Networks for Visual RecognitionCode1
OverFeat: Integrated Recognition, Localization and Detection using Convolutional NetworksCode1
Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image ClassificationCode1
Dynamic Group Convolution for Accelerating Convolutional Neural NetworksCode1
PairAug: What Can Augmented Image-Text Pairs Do for Radiology?Code1
Capsule Network based Contrastive Learning of Unsupervised Visual RepresentationsCode1
FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image RecognitionCode1
Parameter-efficient Model Adaptation for Vision TransformersCode1
Focal Self-attention for Local-Global Interactions in Vision TransformersCode1
Class-Incremental Grouping Network for Continual Audio-Visual LearningCode1
Capsules with Inverted Dot-Product Attention RoutingCode1
FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image ClassificationCode1
Carrying out CNN Channel Pruning in a White BoxCode1
EATFormer: Improving Vision Transformer Inspired by Evolutionary AlgorithmCode1
Partial success in closing the gap between human and machine visionCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Fortuitous Forgetting in Connectionist NetworksCode1
Focal and Global Knowledge Distillation for DetectorsCode1
CLCC: Contrastive Learning for Color ConstancyCode1
Focal Attention for Long-Range Interactions in Vision TransformersCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
ECViT: Efficient Convolutional Vision Transformer with Local-Attention and Multi-scale StagesCode1
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image ClassificationCode1
Category Query Learning for Human-Object Interaction ClassificationCode1
Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial LabelsCode1
Editable Neural NetworksCode1
EEEA-Net: An Early Exit Evolutionary Neural Architecture SearchCode1
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest ImagesCode1
Optimized spiking neurons classify images with high accuracy through temporal coding with two spikesCode1
PDiscoFormer: Relaxing Part Discovery Constraints with Vision TransformersCode1
PDO-eConvs: Partial Differential Operator Based Equivariant ConvolutionsCode1
Forward Learning of Graph Neural NetworksCode1
Efficient Classification of Very Large Images with Tiny ObjectsCode1
Efficiency 360: Efficient Vision TransformersCode1
Efficient Adaptation of Large Vision Transformer via Adapter Re-ComposingCode1
Causal Transportability for Visual RecognitionCode1
Advancing Vision Transformers with Group-Mix AttentionCode1
Permute, Quantize, and Fine-tune: Efficient Compression of Neural NetworksCode1
Mixture-based Feature Space Learning for Few-shot Image ClassificationCode1
Fourier Image TransformerCode1
Efficient Deep Learning of Non-local Features for Hyperspectral Image ClassificationCode1
Benchmarking and scaling of deep learning models for land cover image classificationCode1
Efficient Self-supervised Vision Pretraining with Local Masked ReconstructionCode1
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language ModelCode1
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network CalibrationCode1
Show:102550
← PrevPage 34 of 209Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified