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 18511875 of 10420 papers

TitleStatusHype
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across HeadsCode1
FILIP: Fine-grained Interactive Language-Image Pre-TrainingCode1
Gradient Projection Memory for Continual LearningCode1
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object NavigationCode1
Shredder: Learning Noise Distributions to Protect Inference PrivacyCode1
Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual FeaturesCode1
Gradient Matching for Domain GeneralizationCode1
Gradient Surgery for Multi-Task LearningCode1
CLIP the Gap: A Single Domain Generalization Approach for Object DetectionCode1
Fine-Grained Predicates Learning for Scene Graph GenerationCode1
Fine-grained Recognition with Learnable Semantic Data AugmentationCode1
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image ClassificationCode1
Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained FeaturesCode1
Finetuning CLIP to Reason about Pairwise DifferencesCode1
Gradient Centralization: A New Optimization Technique for Deep Neural NetworksCode1
CLR: Channel-wise Lightweight Reprogramming for Continual LearningCode1
A Fully Tensorized Recurrent Neural NetworkCode1
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
FixCaps: An Improved Capsules Network for Diagnosis of Skin CancerCode1
Gradient-Guided Annealing for Domain GeneralizationCode1
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image ClassificationCode1
Semi-Supervised Classification and Segmentation on High Resolution Aerial ImagesCode1
GradInit: Learning to Initialize Neural Networks for Stable and Efficient TrainingCode1
Show:102550
← PrevPage 75 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