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 126150 of 10419 papers

TitleStatusHype
VSSD: Vision Mamba with Non-Causal State Space DualityCode2
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?Code2
GroupMamba: Efficient Group-Based Visual State Space ModelCode2
DataDream: Few-shot Guided Dataset GenerationCode2
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and TransportationCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
GalLoP: Learning Global and Local Prompts for Vision-Language ModelsCode2
PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent CollaborationCode2
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIPCode2
TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation LearningCode2
WATT: Weight Average Test-Time Adaptation of CLIPCode2
AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image ClassificationCode2
Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%Code2
Unveiling the Power of Wavelets: A Wavelet-based Kolmogorov-Arnold Network for Hyperspectral Image ClassificationCode2
Parameter-Inverted Image Pyramid NetworksCode2
GrootVL: Tree Topology is All You Need in State Space ModelCode2
Why are Visually-Grounded Language Models Bad at Image Classification?Code2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
Accelerating Transformers with Spectrum-Preserving Token MergingCode2
Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern GeneratorsCode2
EMR-Merging: Tuning-Free High-Performance Model MergingCode2
Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image ClassificationCode2
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch NormalizationCode2
Many-Shot In-Context Learning in Multimodal Foundation ModelsCode2
GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNsCode2
Show:102550
← PrevPage 6 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