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 7601–7650 of 10420 papers

TitleStatusHype
Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms—0
Protect Federated Learning Against Backdoor Attacks via Data-Free Trigger Generation—0
Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation—0
Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access—0
Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task—0
Quantized Feature Distillation for Network Quantization—0
Quantum-classical convolutional neural networks in radiological image classification—0
Quantum Entanglement in Deep Learning Architectures—0
Explanation of Unintended Radiated Emission Classification via LIME—0
Learning from Web Data with Self-Organizing Memory Module—0
RAILS: A Robust Adversarial Immune-inspired Learning System—0
RaViTT: Random Vision Transformer Tokens—0
PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification—0
Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training—0
Food Classification using Joint Representation of Visual and Textual Data—0
Assessing Robustness to Noise: Low-Cost Head CT Triage—0
Prototypical Region Proposal Networks for Few-Shot Localization and Classification—0
Pro-tuning: Unified Prompt Tuning for Vision Tasks—0
Active Data Discovery: Mining Unknown Data using Submodular Information Measures—0
Coarse to Fine: Multi-label Image Classification with Global/Local Attention—0
Provable Robustness for Streaming Models with a Sliding Window—0
Trade-offs between membership privacy & adversarially robust learning—0
Provable Uncertainty Decomposition via Higher-Order Calibration—0
Explicitly Modeled Attention Maps for Image Classification—0
Provably efficient neural network representation for image classification—0
Provably Improving Generalization of Few-Shot Models with Synthetic Data—0
FolkTalent: Enhancing Classification and Tagging of Indian Folk Paintings—0
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration—0
Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning—0
Quantifying error contributions of computational steps, algorithms and hyperparameter choices in image classification pipelines—0
Providing Error Detection for Deep Learning Image Classifiers Using Self-Explainability—0
Constrained deep neural network architecture search for IoT devices accounting hardware calibration—0
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting—0
Focusing on the Big Picture: Insights into a Systems Approach to Deep Learning for Satellite Imagery—0
Focused Active Learning for Histopathological Image Classification—0
Prune Responsibly—0
Pruning Convolutional Filters using Batch Bridgeout—0
Pruning Deep Convolutional Neural Network Using Conditional Mutual Information—0
Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks—0
Assessing Pre-trained Models for Transfer Learning through Distribution of Spectral Components—0
Quantifying Task Complexity Through Generalized Information Measures—0
Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features—0
Pruning the Unlabeled Data to Improve Semi-Supervised Learning—0
Exploiting Local Features from Deep Networks for Image Retrieval—0
Exploiting Nontrivial Connectivity for Automatic Speech Recognition—0
Consistent Polyhedral Surrogates for Top-k Classification and Variants—0
FocalLens: Instruction Tuning Enables Zero-Shot Conditional Image Representations—0
Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning—0
A Fully Convolutional Normalization Approach of Head and Neck Cancer Outcome Prediction—0
Consistency-Based Semi-supervised Evidential Active Learning for Diagnostic Radiograph Classification—0
Show:102550
← PrevPage 153 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