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 751–800 of 4925 papers

TitleStatusHype
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
Matching-oriented Product Quantization For Ad-hoc RetrievalCode1
Distributed Learning Systems with First-order MethodsCode1
Quantized Gromov-WassersteinCode1
Network Quantization with Element-wise Gradient ScalingCode1
Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric QuantizerCode1
Integer-only Zero-shot Quantization for Efficient Speech RecognitionCode1
ReCU: Reviving the Dead Weights in Binary Neural NetworksCode1
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAECode1
RangeDet:In Defense of Range View for LiDAR-based 3D Object DetectionCode1
Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted NetworkCode1
Learning Statistical Texture for Semantic SegmentationCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
Self-Distribution Binary Neural NetworksCode1
BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network QuantizationCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
On the Universal Transformation of Data-Driven Models to Control SystemsCode1
Enabling Binary Neural Network Training on the EdgeCode1
Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded PlatformsCode1
Benchmarking Quantized Neural Networks on FPGAs with FINNCode1
SparseDNN: Fast Sparse Deep Learning Inference on CPUsCode1
Binary TTC: A Temporal Geofence for Autonomous NavigationCode1
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointCode1
RangeDet: In Defense of Range View for LiDAR-Based 3D Object DetectionCode1
Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd CountingCode1
A Memory Efficient Baseline for Open Domain Question AnsweringCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN TrainingCode1
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution NetworksCode1
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector QuantizationCode1
Robustness and Transferability of Universal Attacks on Compressed ModelsCode1
Going Beyond Classification Accuracy Metrics in Model CompressionCode1
KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and QuantizationCode1
Fully Quantized Image Super-Resolution NetworksCode1
HAWQV3: Dyadic Neural Network QuantizationCode1
PAMS: Quantized Super-Resolution via Parameterized Max ScaleCode1
Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling DecoderCode1
A Greedy Algorithm for Quantizing Neural NetworksCode1
Accordion: Adaptive Gradient Communication via Critical Learning Regime IdentificationCode1
Permute, Quantize, and Fine-tune: Efficient Compression of Neural NetworksCode1
A Statistical Framework for Low-bitwidth Training of Deep Neural NetworksCode1
ShiftAddNet: A Hardware-Inspired Deep NetworkCode1
Adaptive Gradient Quantization for Data-Parallel SGDCode1
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture SearchCode1
Rotated Binary Neural NetworkCode1
Learning to Improve Image Compression without Changing the Standard DecoderCode1
Adaptive Debanding FilterCode1
Show:102550
← PrevPage 16 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