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 89018950 of 10420 papers

TitleStatusHype
Image Aesthetics Assessment Using Composite Features from off-the-Shelf Deep Models0
Discriminative Pattern Mining for Breast Cancer Histopathology Image Classification via Fully Convolutional Autoencoder0
Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelinesCode0
ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset0
Learning with Inadequate and Incorrect Supervision0
Perceptual Quality-preserving Black-Box Attack against Deep Learning Image ClassifiersCode0
Adversarial Augmentation for Enhancing Classification of Mammography ImagesCode0
Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural NetworksCode0
Adaptive Cross-Modal Few-Shot LearningCode0
LocalNorm: Robust Image Classification through Dynamically Regularized Normalization0
Contextual Encoder-Decoder Network for Visual Saliency PredictionCode0
HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image ClassificationCode0
Min-Entropy Latent Model for Weakly Supervised Object DetectionCode0
Deep Generalized Convolutional Sum-Product NetworksCode0
DC-AL GAN: Pseudoprogression and True Tumor Progression of Glioblastoma Multiform Image Classification Based on DCGAN and AlexNet0
Bayesian Image Classification with Deep Convolutional Gaussian Processes0
Transfusion: Understanding Transfer Learning for Medical ImagingCode0
MultiGrain: a unified image embedding for classes and instancesCode0
On instabilities of deep learning in image reconstruction - Does AI come at a cost?Code0
Integrating Propositional and Relational Label Side Information for Hierarchical Zero-Shot Image Classification0
Graph-RISE: Graph-Regularized Image Semantic Embedding0
Robust Multi-instance Learning with Stable Instances0
Learning to see across Domains and Modalities0
Towards a Robust Deep Neural Network in Texts: A Survey0
Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold0
Deep learning and face recognition: the state of the art0
Meta-CurvatureCode0
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary0
CHIP: Channel-wise Disentangled Interpretation of Deep Convolutional Neural NetworksCode0
Robustness Of Saak Transform Against Adversarial Attacks0
Centroid-based deep metric learning for speaker recognition0
Semi-supervised learning via Feedforward-Designed Convolutional Neural Networks0
Widely Linear Kernels for Complex-Valued Kernel Activation Functions0
Learning Decision Trees Recurrently Through Communication0
Disguised-Nets: Image Disguising for Privacy-preserving Outsourced Deep Learning0
Meta-Amortized Variational Inference and LearningCode0
Towards Pedestrian Detection Using RetinaNet in ECCV 2018 Wider Pedestrian Detection ChallengeCode0
Precise Proximal Femur Fracture Classification for Interactive Training and Surgical Planning0
The Efficacy of SHIELD under Different Threat Models0
ColorNet: Investigating the importance of color spaces for image classificationCode0
Deep Learning Solutions for TanDEM-X-based Forest Classification0
Adaptive Gradient for Adversarial Perturbations Generation0
Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networksCode0
Higher-order Count Sketch: Dimensionality Reduction That Retains Efficient Tensor Operations0
Probabilistic Discriminative Learning with Layered Graphical ModelsCode0
Self-Supervised Visual Representations for Cross-Modal Retrieval0
Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference0
Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 ClassificationCode0
Glyce: Glyph-vectors for Chinese Character RepresentationsCode0
A Push-Pull Layer Improves Robustness of Convolutional Neural Networks0
Show:102550
← PrevPage 179 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