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 38013850 of 10420 papers

TitleStatusHype
ImageNot: A contrast with ImageNet preserves model rankingsCode0
DBIA: Data-free Backdoor Injection Attack against Transformer NetworksCode0
AutoFCL: Automatically Tuning Fully Connected Layers for Handling Small DatasetCode0
Image Quality Assessment Guided Deep Neural Networks TrainingCode0
CoA: Chain-of-Action for Generative Semantic LabelsCode0
Schizophrenia-mimicking layers outperform conventional neural network layersCode0
ImageNet Classification with Deep Convolutional Neural NetworksCode0
Adaptive Activation Functions for Predictive Modeling with Sparse Experimental DataCode0
Implicit Generative Prior for Bayesian Neural NetworksCode0
Dataset Distillation with Infinitely Wide Convolutional NetworksCode0
Dataset Distillation using Neural Feature RegressionCode0
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image SegmentationCode0
Dataset Condensation with Differentiable Siamese AugmentationCode0
Scalable Second Order Optimization for Deep LearningCode0
Dataset Condensation Driven Machine UnlearningCode0
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
Image Classification with Hierarchical Multigraph NetworksCode0
Exploiting Invariance in Training Deep Neural NetworksCode0
Data Representations' Study of Latent Image ManifoldsCode0
AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language ModelsCode0
Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identificationCode0
Data Parameters: A New Family of Parameters for Learning a Differentiable CurriculumCode0
Image Classification Using Singular Value Decomposition and OptimizationCode0
Image classification in frequency domain with 2SReLU: a second harmonics superposition activation functionCode0
Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep ModelsCode0
Aligning Explanations with Human CommunicationCode0
Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network EnsembleCode0
Image Classification with Classic and Deep Learning TechniquesCode0
Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuseCode0
Data-Free Generative Replay for Class-Incremental Learning on Imbalanced DataCode0
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural NetworksCode0
Accelerating Training of Deep Neural Networks with a Standardization LossCode0
ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain AdaptationCode0
Exploring Alternatives to Softmax FunctionCode0
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language TasksCode0
Data-Free Backbone Fine-Tuning for Pruned Neural NetworksCode0
A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image ClassificationCode0
Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive ArchitectureCode0
Data-Efficient Training of CNNs and Transformers with Coresets: A Stability PerspectiveCode0
Data-Efficient Language Shaped Few-shot Image ClassificationCode0
On the Limitations of Temperature Scaling for Distributions with OverlapsCode0
A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep LearningCode0
Image-Caption Encoding for Improving Zero-Shot GeneralizationCode0
A Unified View of Masked Image ModelingCode0
Identifying Transients in the Dark Energy Survey using Convolutional Neural NetworksCode0
Identifying Adversarially Attackable and Robust SamplesCode0
Identifying Bias in Deep Neural Networks Using Image TransformsCode0
Exploring Gradient Flow Based Saliency for DNN Model CompressionCode0
IDEA: Image Description Enhanced CLIP-AdapterCode0
Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image ClassificationCode0
Show:102550
← PrevPage 77 of 209Next →

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