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 38013810 of 10420 papers

TitleStatusHype
Distilled Gradual Pruning with Pruned Fine-tuningCode0
Balancing the Causal Effects in Class-Incremental Learning0
Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment0
What to Do When Your Discrete Optimization Is the Size of a Neural Network?Code0
Investigation of Federated Learning Algorithms for Retinal Optical Coherence Tomography Image Classification with Statistical HeterogeneityCode0
ViGEO: an Assessment of Vision GNNs in Earth ObservationCode0
Hybrid CNN Bi-LSTM neural network for Hyperspectral image classification0
Reducing Texture Bias of Deep Neural Networks via Edge Enhancing DiffusionCode0
Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lagCode0
I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption0
Show:102550
← PrevPage 381 of 1042Next →

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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified