SOTAVerified

Quantization

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2076–2100 of 4925 papers

TitleStatusHype
Communication and Energy Efficient Federated Learning using Zero-Order Optimization Technique—0
Extreme Image Compression using Fine-tuned VQGANs—0
COMET: Towards Partical W4A4KV4 LLMs Serving—0
Extreme Compression for Pre-trained Transformers Made Simple and Efficient—0
Post Training Quantization of Large Language Models with Microscaling Formats—0
Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising—0
Exposing Hardware Building Blocks to Machine Learning Frameworks—0
Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks—0
A QP-adaptive Mechanism for CNN-based Filter in Video Coding—0
AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence—0
Exploring Semantic Segmentation on the DCT Representation—0
Collaborative Quantization for Cross-Modal Similarity Search—0
Collaborative Quantization Embeddings for Intra-Subject Prostate MR Image Registration—0
Exploring Neural Networks Quantization via Layer-Wise Quantization Analysis—0
Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization—0
Collaborative Multi-Teacher Knowledge Distillation for Learning Low Bit-width Deep Neural Networks—0
APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models—0
A Data and Compute Efficient Design for Limited-Resources Deep Learning—0
Exploring FPGA designs for MX and beyond—0
Exploring Extreme Quantization in Spiking Language Models—0
Collaborative Filtering with Smooth Reconstruction of the Preference Function—0
Exploring Automatic Gym Workouts Recognition Locally On Wearable Resource-Constrained Devices—0
Collaborative Edge AI Inference over Cloud-RAN—0
Explore the Potential of CNN Low Bit Training—0
Explore Cross-Codec Quality-Rate Convex Hulls Relation for Adaptive Streaming—0
Show:102550
← PrevPage 84 of 197Next →
All datasetsImageNetCIFAR-10Wiki-40BAgeDB-30CFP-FPCOCO (Common Objects in Context)IJB-BIJB-CKnowledge-based:LFW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03—Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31—Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97—Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71—Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2—Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51—Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17—Unverified
8Xception W8A8Top-1 Accuracy (%)78.97—Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88—Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04—Unverified
2DTQMAP0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3—Unverified
2OutEffHop-Bert_basePerplexity6.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92—Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8—Unverified