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 52015225 of 10420 papers

TitleStatusHype
Addressing out-of-distribution label noise in webly-labelled data0
Defensive Tensorization0
VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks0
MUSE: Feature Self-Distillation with Mutual Information and Self-Information0
ZerO Initialization: Initializing Neural Networks with only Zeros and OnesCode1
Instance-Conditional Knowledge Distillation for Object DetectionCode1
Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation0
Some like it tough: Improving model generalization via progressively increasing the training difficultyCode0
Exploring Gradient Flow Based Saliency for DNN Model CompressionCode0
Generalized Resubstitution for Classification Error Estimation0
MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited LabelsCode1
Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image RecognitionCode0
Game of Gradients: Mitigating Irrelevant Clients in Federated LearningCode0
A Simple Baseline for Low-Budget Active LearningCode1
Federated Unlearning via Class-Discriminative PruningCode0
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy LabelsCode0
Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer AggregationCode1
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators0
Sinkformers: Transformers with Doubly Stochastic AttentionCode1
GCCN: Global Context Convolutional Network0
Signature-Graph Networks0
EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification TaskCode0
FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion0
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
Improving the Deployment of Recycling Classification through Efficient Hyper-Parameter Analysis0
Show:102550
← PrevPage 209 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