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 7076–7100 of 10420 papers

TitleStatusHype
Neighbor Class Consistency on Unsupervised Domain Adaptation—0
Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks—0
Category Disentangled Context: Turning Category-irrelevant Features Into Treasures—0
Dual-Tree Wavelet Packet CNNs for Image Classification—0
More Side Information, Better Pruning: Shared-Label Classification as a Case Study—0
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces—0
Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher—0
MoCo-Pretraining Improves Representations and Transferability of Chest X-ray Models—0
Domain-Invariant Disentangled Network for Generalizable Object Detection—0
Buffer Zone based Defense against Adversarial Examples in Image Classification—0
Distilling Global and Local Logits With Densely Connected RelationsCode0
Maximum Categorical Cross Entropy (MCCE): A noise-robust alternative loss function to mitigate racial bias in Convolutional Neural Networks (CNNs) by reducing overfitting—0
LLBoost: Last Layer Perturbation to Boost Pre-trained Neural Networks—0
Lipschitz-Bounded Equilibrium Networks—0
DIET-SNN: A Low-Latency Spiking Neural Network with Direct Input Encoding & Leakage and Threshold Optimization—0
Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples—0
Detection Booster Training: A detection booster training method for improving the accuracy of classifiers.—0
Learning the Connections in Direct Feedback Alignment—0
Learning Representation in Colour Conversion—0
TwinDNN: A Tale of Two Deep Neural Networks—0
Learning from multiscale wavelet superpixels using GNN with spatially heterogeneous pooling—0
Demystifying Loss Functions for Classification—0
Optimal allocation of data across training tasks in meta-learning—0
Deep Repulsive Clustering of Ordered Data Based on Order-Identity Decomposition—0
The Foes of Neural Network’s Data Efficiency Among Unnecessary Input Dimensions—0
Show:102550
← PrevPage 284 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
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified