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 14761500 of 10420 papers

TitleStatusHype
FACMIC: Federated Adaptative CLIP Model for Medical Image ClassificationCode1
Bilinear MLPs enable weight-based mechanistic interpretabilityCode1
LightViT: Towards Light-Weight Convolution-Free Vision TransformersCode1
Fair Contrastive Learning for Facial Attribute ClassificationCode1
AdaViT: Adaptive Tokens for Efficient Vision TransformerCode1
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and PhysicsCode1
LiteGPT: Large Vision-Language Model for Joint Chest X-ray Localization and Classification TaskCode1
Can Biases in ImageNet Models Explain Generalization?Code1
BinaryViT: Pushing Binary Vision Transformers Towards Convolutional ModelsCode1
Deep Multimodal Guidance for Medical Image ClassificationCode1
LLMs as Visual Explainers: Advancing Image Classification with Evolving Visual DescriptionsCode1
Can Language Understand Depth?Code1
LocalViT: Bringing Locality to Vision TransformersCode1
Deep Networks with Stochastic DepthCode1
Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal EffectCode1
DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep LearningCode1
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide ImagesCode1
BionoiNet: ligand-binding site classification with off-the-shelf deep neural networkCode1
High-parallelism Inception-like Spiking Neural Networks for Unsupervised Feature LearningCode1
Deep Polynomial Neural NetworksCode1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
LPT: Long-tailed Prompt Tuning for Image ClassificationCode1
Extending CAM-based XAI methods for Remote Sensing Imagery SegmentationCode1
Eye-gaze Guided Multi-modal Alignment for Medical Representation LearningCode1
Show:102550
← PrevPage 60 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