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 90519075 of 10420 papers

TitleStatusHype
Moving from 2D to 3D: volumetric medical image classification for rectal cancer stagingCode0
Implicit Generative Prior for Bayesian Neural NetworksCode0
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuseCode0
Soft ascent-descent as a stable and flexible alternative to floodingCode0
Distilling Global and Local Logits With Densely Connected RelationsCode0
Importance of Disjoint Sampling in Conventional and Transformer Models for Hyperspectral Image ClassificationCode0
Assessing Sample Quality via the Latent Space of Generative ModelsCode0
Chest X-Ray Images Classification with CNNCode0
MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of GradientsCode0
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time DetectionCode0
ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic SegmentationCode0
Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation ModelsCode0
Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and RegressionCode0
RAFIC: Retrieval-Augmented Few-shot Image ClassificationCode0
ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious CorrelationsCode0
MRSCAtt: A Spatio-Channel Attention-Guided Network for Mars Rover Image ClassificationCode0
Improved efficient capsule network for Kuzushiji-MNIST benchmark dataset classificationCode0
Path-Level Network Transformation for Efficient Architecture SearchCode0
Rafiki: Machine Learning as an Analytics Service SystemCode0
Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR ModelsCode0
Anytime Inference with Distilled Hierarchical Neural EnsemblesCode0
Improved Gradient based Adversarial Attacks for Quantized NetworksCode0
Adaptive Learning Rate and Momentum for Training Deep Neural NetworksCode0
CHEF: A Cheap and Fast Pipeline for Iteratively Cleaning Label Uncertainties (Technical Report)Code0
Characterizing Bias in Classifiers using Generative ModelsCode0
Show:102550
← PrevPage 363 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