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
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference TimeCode1
Federated Learning via Plurality VoteCode0
8-bit Optimizers via Block-wise QuantizationCode3
Shifting Capsule Networks from the Cloud to the Deep EdgeCode0
Random matrices in service of ML footprint: ternary random features with no performance lossCode1
Attention Augmented Convolutional Transformer for Tabular Time-series—0
FedDQ: Communication-Efficient Federated Learning with Descending Quantization—0
Pre-Quantized Deep Learning Models Codified in ONNX to Enable Hardware/Software Co-Design—0
SDR: Efficient Neural Re-ranking using Succinct Document Representation—0
Beyond Neighbourhood-Preserving Transformations for Quantization-Based Unsupervised Hashing—0
Towards Efficient Post-training Quantization of Pre-trained Language Models—0
Riemannian Manifold Embeddings for Straight-Through Estimator—0
Full-Precision Free Binary Graph Neural Networks—0
Beyond Quantization: Power aware neural networks—0
Faster Neural Net Inference via Forests of Sparse Oblique Decision Trees—0
Delving into Channels: Exploring Hyperparameter Space of Channel Bit Widths with Linear Complexity—0
PIVQGAN: Posture and Identity Disentangled Image-to-Image Translation via Vector Quantization—0
Post-Training Quantization Is All You Need to Perform Cross-Platform Learned Image Compression—0
Lattice Quantization—0
Quantized sparse PCA for neural network weight compression—0
Wavelet Feature Maps Compression for Low Bandwidth Convolutional Neural Networks—0
Contrastive Mutual Information Maximization for Binary Neural Networks—0
Specialized Transformers: Faster, Smaller and more Accurate NLP Models—0
Logarithmic Unbiased Quantization: Practical 4-bit Training in Deep Learning—0
Succinct Compression: Near-Optimal and Lossless Compression of Deep Neural Networks during Inference Runtime—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