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 3251–3300 of 4925 papers

TitleStatusHype
Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information—0
Towards Real-Time Neural Volumetric Rendering on Mobile Devices: A Measurement Study—0
Towards Reasoning Ability of Small Language Models—0
Towards Robust Low Light Image Enhancement—0
Towards Semantic Communications: Deep Learning-Based Image Semantic Coding—0
Towards Superior Quantization Accuracy: A Layer-sensitive Approach—0
Towards the Limit of Network Quantization—0
Towards Unified INT8 Training for Convolutional Neural Network—0
Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning—0
Towards Variable and Coordinated Holistic Co-Speech Motion Generation—0
Towards Watermarking of Open-Source LLMs—0
TP-Aware Dequantization—0
TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers—0
Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs—0
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers—0
Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models—0
Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization—0
Training and Inference for Integer-Based Semantic Segmentation Network—0
Training DNN IoT Applications for Deployment On Analog NVM Crossbars—0
Training Integer-Only Deep Recurrent Neural Networks—0
Training of mixed-signal optical convolutional neural network with reduced quantization level—0
Training Quantized Neural Networks with a Full-precision Auxiliary Module—0
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming—0
Training with reduced precision of a support vector machine model for text classification—0
Transceiver Cooperative Learning-aided Semantic Communications Against Mismatched Background Knowledge Bases—0
Transferable Sequential Recommendation via Vector Quantized Meta Learning—0
Transfer Hashing with Privileged Information—0
Transformations in Learned Image Compression from a Modulation Perspective—0
Transform-Based Feature Map Compression for CNN Inference—0
Transformed Residual Quantization for Approximate Nearest Neighbor Search—0
Transformer-based Clipped Contrastive Quantization Learning for Unsupervised Image Retrieval—0
Transformer-based models and hardware acceleration analysis in autonomous driving: A survey—0
Transformer-Based Nonlinear Transform Coding for Multi-Rate CSI Compression in MIMO-OFDM Systems—0
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs—0
Transform Quantization for CNN (Convolutional Neural Network) Compression—0
Transition Rate Scheduling for Quantization-Aware Training—0
Transmitting Data Through Reconfigurable Intelligent Surface: A Spatial Sigma-Delta Modulation Approach—0
TR-DQ: Time-Rotation Diffusion Quantization—0
T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit—0
Tree Index: A New Cluster Evaluation Technique—0
Tree Quantization for Large-Scale Similarity Search and Classification—0
Triagem virtual de imagens de imuno-histoquímica usando redes neurais artificiais e espectro de padrões—0
TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs—0
Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search—0
TriplePlay: Enhancing Federated Learning with CLIP for Non-IID Data and Resource Efficiency—0
TripleSpin - a generic compact paradigm for fast machine learning computations—0
TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs—0
Truncated Non-Uniform Quantization for Distributed SGD—0
Semantic-Enabled 6G Communication: A Task-oriented and Privacy-preserving Perspective—0
TSPTQ-ViT: Two-scaled post-training quantization for vision transformer—0
Show:102550
← PrevPage 66 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