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 86768700 of 10420 papers

TitleStatusHype
Adaptively Connected Neural NetworksCode0
C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning0
Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift0
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 HoursCode0
Relation-Aware Global Attention for Person Re-identificationCode0
A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning0
On Direct Distribution Matching for Adapting Segmentation Networks0
Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification0
Video Classification with Channel-Separated Convolutional NetworksCode0
Understanding the efficacy, reliability and resiliency of computer vision techniques for malware detection and future research directions0
Hyperbolic Image EmbeddingsCode1
Correlation Congruence for Knowledge DistillationCode0
A Comprehensive Overhaul of Feature DistillationCode0
Exploring Randomly Wired Neural Networks for Image RecognitionCode0
Looking back at Labels: A Class based Domain Adaptation TechniqueCode0
Augmented Neural ODEsCode1
C2AE: Class Conditioned Auto-Encoder for Open-set Recognition0
Res2Net: A New Multi-scale Backbone ArchitectureCode1
Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation0
Weakly Supervised Object Detection with Segmentation Collaboration0
Variational Adversarial Active LearningCode1
IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance MattersCode1
Deep Convolutional Spiking Neural Networks for Image Classification0
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot LearningCode0
Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration0
Show:102550
← PrevPage 348 of 417Next →

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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified