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 3176–3200 of 4925 papers

TitleStatusHype
Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases—0
Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs—0
Understanding the Impact of Post-Training Quantization on Large Language Models—0
Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks—0
Understanding Unconventional Preprocessors in Deep Convolutional Neural Networks for Face Identification—0
UniCode: Learning a Unified Codebook for Multimodal Large Language Models—0
UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation—0
Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization—0
Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization—0
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning—0
Unified learning-based lossy and lossless JPEG recompression—0
Unified Stochastic Framework for Neural Network Quantization and Pruning—0
Uniform-Precision Neural Network Quantization via Neural Channel Expansion—0
Unifying KV Cache Compression for Large Language Models with LeanKV—0
UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion—0
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes—0
UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks—0
Universal Deep Neural Network Compression—0
Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size—0
Universal Joint Source-Channel Coding for Modulation-Agnostic Semantic Communication—0
Universally Quantized Neural Compression—0
Unleashing Dynamic Range and Resolution in Unlimited Sensing Framework via Novel Hardware—0
Unlimited Sampling Radar: a Real-Time End-to-End Demonstrator—0
Unlocking Efficient Large Inference Models: One-Bit Unrolling Tips the Scales—0
Enhancing Multimodal Unified Representations for Cross Modal Generalization—0
Show:102550
← PrevPage 128 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