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 10201–10250 of 10420 papers

TitleStatusHype
Learning to Detect Malicious Clients for Robust Federated Learning—0
Learning to Detect Semantic Boundaries with Image-level Class Labels—0
Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks—0
Learning to Generate Image Embeddings with User-level Differential Privacy—0
Learning to Generate Images with Perceptual Similarity Metrics—0
Learning to generate imaginary tasks for improving generalization in meta-learning—0
Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing—0
Learning to Learn: How to Continuously Teach Humans and Machines—0
Learning to Learn Image Classifiers with Visual Analogy—0
Learning to Learn Semantic Factors in Heterogeneous Image Classification—0
Learning to Model the Tail—0
Learning to Name Classes for Vision and Language Models—0
Learning to predict visual brain activity by predicting future sensory states—0
Learning to Rank for Active Learning: A Listwise Approach—0
Learning to Sample: an Active Learning Framework—0
Learning to Schedule Learning rate with Graph Neural Networks—0
Learning to see across Domains and Modalities—0
Learning to See Physical Properties with Active Sensing Motor Policies—0
Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning—0
Learning to Specialize with Knowledge Distillation for Visual Question Answering—0
Learning to Teach—0
Learning to Reweight with Deep Interactions—0
Learning to Teach with Dynamic Loss Functions—0
Learning to Utilize Correlated Auxiliary Noise: A Possible Quantum Advantage—0
Learning transformer-based heterogeneously salient graph representation for multimodal remote sensing image classification—0
Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptation—0
Learning Wake-Sleep Recurrent Attention Models—0
Learning What Data to Learn—0
Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision—0
Continual Learning with Evolving Class Ontologies—0
Learning with convolution and pooling operations in kernel methods—0
Learning with Differentiable Algorithms—0
Learning with Hierarchical Complement Objective—0
Learning with Inadequate and Incorrect Supervision—0
Learning with Label Noise for Image Retrieval by Selecting Interactions—0
Learning with Limited Samples -- Meta-Learning and Applications to Communication Systems—0
Learning with Neighbor Consistency for Noisy Labels—0
Learning with Noisy Ground Truth: From 2D Classification to 3D Reconstruction—0
Learning with Recursive Perceptual Representations—0
Learning with SASQuaTCh: a Novel Variational Quantum Transformer Architecture with Kernel-Based Self-Attention—0
Learn like a Pathologist: Curriculum Learning by Annotator Agreement for Histopathology Image Classification—0
Learn to Predict Sets Using Feed-Forward Neural Networks—0
LeDNet: Localization-enabled Deep Neural Network for Multi-Label Radiography Image Classification—0
Lensless-camera based machine learning for image classification—0
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations—0
Lesion2Vec: Deep Metric Learning for Few-Shot Multiple Lesions Recognition in Wireless Capsule Endoscopy Video—0
Less-forgetful Learning for Domain Expansion in Deep Neural Networks—0
Training Data Subset Search with Ensemble Active Learning—0
Less is More: Dimension Reduction Finds On-Manifold Adversarial Examples in Hard-Label Attacks—0
Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification—0
Show:102550
← PrevPage 205 of 209Next →
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