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 19011925 of 10420 papers

TitleStatusHype
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over ModulesCode1
Heteroskedastic and Imbalanced Deep Learning with Adaptive RegularizationCode1
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network ArchitecturesCode1
Image Classification by Reinforcement Learning with Two-State Q-LearningCode1
ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural NetworksCode1
Learning Data Augmentation with Online Bilevel Optimization for Image ClassificationCode1
Deep Prototypical Networks with Hybrid Residual Attention for Hyperspectral Image ClassificationCode1
Normalized Loss Functions for Deep Learning with Noisy LabelsCode1
Learning Semantically Enhanced Feature for Fine-Grained Image ClassificationCode1
Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box AttacksCode1
Compositional Explanations of NeuronsCode1
Calibration of Neural Networks using SplinesCode1
On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AIDCode1
The color out of space: learning self-supervised representations for Earth Observation imageryCode1
Self-Knowledge Distillation with Progressive Refinement of TargetsCode1
DO-Conv: Depthwise Over-parameterized Convolutional LayerCode1
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture SearchCode1
A Universal Representation Transformer Layer for Few-Shot Image ClassificationCode1
Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble DistillationCode1
Deep Polynomial Neural NetworksCode1
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual RecognitionCode1
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction DetectionCode1
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group SoftmaxCode1
Tent: Fully Test-time Adaptation by Entropy MinimizationCode1
Show:102550
← PrevPage 77 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