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 851875 of 10419 papers

TitleStatusHype
Universal Domain Adaptation for Remote Sensing Image Scene ClassificationCode1
Trainable Activations for Image ClassificationCode1
ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on GradientsCode1
Discovering and Mitigating Visual Biases through Keyword ExplanationCode1
Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance AssessmentCode1
Discriminator-free Unsupervised Domain Adaptation for Multi-label Image ClassificationCode1
Lightweight Neural Architecture Search for Temporal Convolutional Networks at the EdgeCode1
Local Window Attention Transformer for Polarimetric SAR Image ClassificationCode1
Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image ClassificationCode1
Modeling Uncertain Feature Representation for Domain GeneralizationCode1
CLIP the Gap: A Single Domain Generalization Approach for Object DetectionCode1
Dynamic Grained Encoder for Vision TransformersCode1
Learning Support and Trivial Prototypes for Interpretable Image ClassificationCode1
MoBYv2AL: Self-supervised Active Learning for Image ClassificationCode1
TinyMIM: An Empirical Study of Distilling MIM Pre-trained ModelsCode1
Knockoffs-SPR: Clean Sample Selection in Learning with Noisy LabelsCode1
Class-Aware Patch Embedding Adaptation for Few-Shot Image ClassificationCode1
Rate Gradient Approximation Attack Threats Deep Spiking Neural NetworksCode1
ViewNet: A Novel Projection-Based Backbone With View Pooling for Few-Shot Point Cloud ClassificationCode1
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced DataCode1
Efficient On-device Training via Gradient FilteringCode1
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse RetrievalCode1
DISC: Learning From Noisy Labels via Dynamic Instance-Specific Selection and CorrectionCode1
PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image ClassificationCode1
AdaptiveMix: Improving GAN Training via Feature Space ShrinkageCode1
Show:102550
← PrevPage 35 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified