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 18011825 of 10420 papers

TitleStatusHype
MCA: Moment Channel Attention NetworksCode0
Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image ClassificationCode1
NiNformer: A Network in Network Transformer with Token Mixing Generated Gating FunctionCode0
DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time ScalingCode0
When do Convolutional Neural Networks Stop Learning?Code0
Transformers for Supervised Online Continual Learning0
Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision0
ELA: Efficient Local Attention for Deep Convolutional Neural Networks0
Can a Confident Prior Replace a Cold Posterior?Code0
Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation0
VisionLLaMA: A Unified LLaMA Backbone for Vision TasksCode3
SURE: SUrvey REcipes for building reliable and robust deep networksCode2
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation ModelCode0
Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification0
Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic InteractionCode1
HyenaPixel: Global Image Context with ConvolutionsCode0
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious CorrelationCode0
Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance0
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling0
Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains0
Classes Are Not Equal: An Empirical Study on Image Recognition Fairness0
Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization0
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric EstimationCode0
Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers0
Scaling Supervised Local Learning with Augmented Auxiliary NetworksCode0
Show:102550
← PrevPage 73 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
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