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 8151–8200 of 10420 papers

TitleStatusHype
DeepAGREL: Biologically plausible deep learning via direct reinforcement—0
AdaScale SGD: A Scale-Invariant Algorithm for Distributed Training—0
Defensive Tensorization: Randomized Tensor Parametrization for Robust Neural Networks—0
Adaptive Data Augmentation with Deep Parallel Generative Models—0
Monte Carlo Deep Neural Network Arithmetic—0
Smart Ternary Quantization—0
Training Data Distribution Search with Ensemble Active Learning—0
Test-Time Training for Out-of-Distribution Generalization—0
Siamese Attention Networks—0
When Robustness Doesn’t Promote Robustness: Synthetic vs. Natural Distribution Shifts on ImageNet—0
Scalable Deep Neural Networks via Low-Rank Matrix Factorization—0
SoftAdam: Unifying SGD and Adam for better stochastic gradient descent—0
Unknown-Aware Deep Neural Network—0
Scale-Equivariant Neural Networks with Decomposed Convolutional Filters—0
Diving into Optimization of Topology in Neural Networks—0
Model-Agnostic Feature Selection with Additional Mutual Information—0
Laconic Image Classification: Human vs. Machine Performance—0
Evo-NAS: Evolutionary-Neural Hybrid Agent for Architecture Search—0
A Kolmogorov Complexity Approach to Generalization in Deep Learning—0
Data Augmentation in Training CNNs: Injecting Noise to Images—0
Distance-based Composable Representations with Neural Networks—0
Learning in Confusion: Batch Active Learning with Noisy Oracle—0
Invariance vs Robustness of Neural Networks—0
Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep NetworksCode0
Gated Channel Transformation for Visual RecognitionCode0
Beyond image classification: zooplankton identification with deep vector space embeddings—0
Non-imaging single-pixel sensing with optimized binary modulation—0
PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex DomainCode0
Anchor Loss: Modulating Loss Scale based on Prediction DifficultyCode0
Image Recognition using Region Creep—0
Constrained deep neural network architecture search for IoT devices accounting hardware calibration—0
Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World—0
Unsupervised Deep Features for Privacy Image Classification—0
Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters—0
AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning—0
Tag-based Semantic Features for Scene Image Classification—0
A Layered Architecture for Active Perception: Image Classification using Deep Reinforcement Learning—0
Understanding and Robustifying Differentiable Architecture SearchCode0
Defending Against Physically Realizable Attacks on Image ClassificationCode0
Understanding Architectures Learnt by Cell-based Neural Architecture SearchCode0
Toward Robust Image Classification—0
Timage -- A Robust Time Series Classification PipelineCode0
Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data—0
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLCode1
Utilizing Dependence among Variables in Evolutionary Algorithms for Mixed-Integer Programming: A Case Study on Multi-Objective Constrained Portfolio Optimization—0
Large e-retailer image dataset for visual search and product classification—0
Ludwig: a type-based declarative deep learning toolboxCode3
Transfer Learning with Dynamic Distribution Adaptation—0
They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimization—0
Classification-Specific Parts for Improving Fine-Grained Visual CategorizationCode0
Show:102550
← PrevPage 164 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