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 3801–3850 of 4925 papers

TitleStatusHype
Bernoulli Embeddings for Graphs—0
BeST -- A Novel Source Selection Metric for Transfer Learning—0
Better Schedules for Low Precision Training of Deep Neural Networks—0
Beyond Discreteness: Finite-Sample Analysis of Straight-Through Estimator for Quantization—0
Beyond Neighbourhood-Preserving Transformations for Quantization-Based Unsupervised Hashing—0
Beyond Quantization: Power aware neural networks—0
Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics—0
Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models—0
Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression—0
BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration—0
BICM-compatible Rate Adaptive Geometric Constellation Shaping Using Optimized Many-to-one Labeling—0
Bielik 11B v2 Technical Report—0
Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization—0
SpeedLimit: Neural Architecture Search for Quantized Transformer Models—0
BiLiMO: Bit-Limited MIMO Radar via Task-Based Quantization—0
Bilinear Random Projections for Locality-Sensitive Binary Codes—0
Binarized Neural Network for Single Image Super Resolution—0
Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis—0
BinaryBERT: Pushing the Limit of BERT Quantization—0
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation—0
Binary Neural Network for Speaker Verification—0
Binary Neural Networks as a general-propose compute paradigm for on-device computer vision—0
BinaryViT: Towards Efficient and Accurate Binary Vision Transformers—0
Bioinspired Cortex-based Fast Codebook Generation—0
Biologically Plausible Learning on Neuromorphic Hardware Architectures—0
BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs—0
BiSup: Bidirectional Quantization Error Suppression for Large Language Models—0
BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation—0
Bit Efficient Quantization for Deep Neural Networks—0
Bit-Mixer: Mixed-precision networks with runtime bit-width selection—0
BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks—0
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization—0
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model—0
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization—0
BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing—0
Bi-ViT: Pushing the Limit of Vision Transformer Quantization—0
Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks—0
Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generation—0
Blind-Adaptive Quantizers—0
Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms—0
Blockwise Compression of Transformer-based Models without Retraining—0
Block-Wise Dynamic-Precision Neural Network Training Acceleration via Online Quantization Sensitivity Analytics—0
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices—0
BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch—0
BOMP-NAS: Bayesian Optimization Mixed Precision NAS—0
Boost CTR Prediction for New Advertisements via Modeling Visual Content—0
Boosted Dense Retriever—0
Boosted Dense Retriever—0
Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication—0
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization—0
Show:102550
← PrevPage 77 of 99Next →
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