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 14511500 of 10419 papers

TitleStatusHype
Improved Generation of Adversarial Examples Against Safety-aligned LLMsCode1
DAM: Dynamic Adapter Merging for Continual Video QA LearningCode1
Improved Noisy Student Training for Automatic Speech RecognitionCode1
Improved Online Conformal Prediction via Strongly Adaptive Online LearningCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?Code1
AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingCode1
Class-Balanced Loss Based on Effective Number of SamplesCode1
An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural NetworksCode1
Class-Balanced Distillation for Long-Tailed Visual RecognitionCode1
Revisiting the Importance of Amplifying Bias for DebiasingCode1
Bias Loss for Mobile Neural NetworksCode1
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised PretrainingCode1
BiasPruner: Debiased Continual Learning for Medical Image ClassificationCode1
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image ClassificationCode1
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image ClassificationCode1
Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image ClassificationCode1
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution EnvironmentsCode1
A General Regret Bound of Preconditioned Gradient Method for DNN TrainingCode1
DARTS: Differentiable Architecture SearchCode1
Object Segmentation Without Labels with Large-Scale Generative ModelsCode1
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic SegmentationCode1
Big Self-Supervised Models Advance Medical Image ClassificationCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
Bilinear MLPs enable weight-based mechanistic interpretabilityCode1
Incorporating Convolution Designs into Visual TransformersCode1
Billion-scale semi-supervised learning for image classificationCode1
AdaViT: Adaptive Tokens for Efficient Vision TransformerCode1
Information Bottleneck Approach to Spatial Attention LearningCode1
Information Maximization Clustering via Multi-View Self-LabellingCode1
CvT: Introducing Convolutions to Vision TransformersCode1
BinaryViT: Pushing Binary Vision Transformers Towards Convolutional ModelsCode1
Instance Localization for Self-supervised Detection PretrainingCode1
Instance Similarity Learning for Unsupervised Feature RepresentationCode1
Interpolation between Residual and Non-Residual NetworksCode1
Interpretability-Aware Vision TransformerCode1
Interpretable Image Classification with Differentiable Prototypes AssignmentCode1
Interpretable Image Classification with Adaptive Prototype-based Vision TransformersCode1
Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual KnowledgeCode1
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution LayersCode1
Introspective Deep Metric Learning for Image RetrievalCode1
BionoiNet: ligand-binding site classification with off-the-shelf deep neural networkCode1
Curriculum Temperature for Knowledge DistillationCode1
Investigating and Explaining the Frequency Bias in Image ClassificationCode1
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingCode1
Iranis: A Large-scale Dataset of Farsi License Plate CharactersCode1
Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image ClassificationCode1
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Show:102550
← PrevPage 30 of 209Next →

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