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 3076–3100 of 10420 papers

TitleStatusHype
Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural NetworksCode0
Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per classCode0
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
DartsReNet: Exploring new RNN cells in ReNet architecturesCode0
Improving Image Recognition by Retrieving from Web-Scale Image-Text Data—0
Neural Delay Differential Equations: System Reconstruction and Image Classification—0
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual RecognitionCode2
Asymmetric Polynomial Loss For Multi-Label ClassificationCode1
Are Visual Recognition Models Robust to Image Compression?—0
Use the Detection Transformer as a Data AugmenterCode0
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning—0
Arithmetic Intensity Balancing Convolution for Hardware-aware Efficient Block Design—0
Universal Semi-Supervised Learning for Medical Image ClassificationCode0
RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks—0
Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning—0
MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for VisionCode0
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Adaptive Mask Sampling and Manifold to Euclidean Subspace Learning with Distance Covariance Representation for Hyperspectral Image ClassificationCode1
Can we learn better with hard samples?Code0
PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift—0
SparseFormer: Sparse Visual Recognition via Limited Latent TokensCode1
Meta-causal Learning for Single Domain Generalization—0
ElegansNet: a brief scientific report and initial experiments—0
Source-free Domain Adaptation Requires Penalized Diversity—0
ImageEye: Batch Image Processing Using Program Synthesis—0
Show:102550
← PrevPage 124 of 417Next →
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