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 2001–2025 of 4925 papers

TitleStatusHype
Bandwidth-efficient Inference for Neural Image Compression—0
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models—0
RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems—0
QuantEase: Optimization-based Quantization for Language Models—0
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks—0
A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking—0
Compressing Vision Transformers for Low-Resource Visual LearningCode0
On the fly Deep Neural Network Optimization Control for Low-Power Computer Vision—0
Softmax Bias Correction for Quantized Generative Models—0
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models—0
Few shot font generation via transferring similarity guided global style and quantization local styleCode1
RepCodec: A Speech Representation Codec for Speech TokenizationCode1
SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language ModelsCode2
Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector QuantizationCode0
FPTQ: Fine-grained Post-Training Quantization for Large Language Models—0
Implementation and Evaluation of Physical Layer Key Generation on SDR based LoRa Platform—0
Continual Learning for Generative Retrieval over Dynamic CorporaCode0
Uncovering the Hidden Cost of Model CompressionCode0
On-Device Learning with Binary Neural Networks—0
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message PropagationCode0
Maestro: Uncovering Low-Rank Structures via Trainable DecompositionCode0
MEMORY-VQ: Compression for Tractable Internet-Scale Memory—0
VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and QuantizationCode1
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsCode2
Efficient Learned Lossless JPEG Recompression—0
Show:102550
← PrevPage 81 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