SOTAVerified

Model Compression

Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–550 of 1356 papers

TitleStatusHype
MobileNMT: Enabling Translation in 15MB and 30msCode1
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference—0
Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation—0
Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet—0
Group channel pruning and spatial attention distilling for object detection—0
Task-Agnostic Structured Pruning of Speech Representation Models—0
LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-TuningCode1
ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval—0
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision ModelsCode1
2-bit Conformer quantization for automatic speech recognition—0
RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models—0
An Efficient Multilingual Language Model Compression through Vocabulary TrimmingCode1
PruMUX: Augmenting Data Multiplexing with Model CompressionCode0
Selective Pre-training for Private Fine-tuningCode0
Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study—0
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt—0
AD-KD: Attribution-Driven Knowledge Distillation for Language Model CompressionCode1
Towards Understanding and Improving Knowledge Distillation for Neural Machine TranslationCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation—0
Redundancy and Concept Analysis for Code-trained Language Models—0
CORSD: Class-Oriented Relational Self Distillation—0
Guaranteed Quantization Error Computation for Neural Network Model Compression—0
Class Attention Transfer Based Knowledge DistillationCode1
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures—0
Deep Collective Knowledge Distillation—0
Learning Accurate Performance Predictors for Ultrafast Automated Model CompressionCode0
Structured Pruning for Multi-Task Deep Neural Networks—0
Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning—0
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes—0
A Multi-objective Complex Network Pruning Framework Based on Divide-and-conquer and Global Performance Impairment Ranking—0
Tetra-AML: Automatic Machine Learning via Tensor Networks—0
Information-Theoretic GAN Compression with Variational Energy-based Model—0
Towards Accurate Post-Training Quantization for Vision Transformer—0
Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training—0
Exploring Turkish Speech Recognition via Hybrid CTC/Attention Architecture and Multi-feature Fusion Network—0
Performance-aware Approximation of Global Channel Pruning for Multitask CNNsCode1
The Tiny Time-series Transformer: Low-latency High-throughput Classification of Astronomical Transients using Deep Model CompressionCode1
R2 Loss: Range Restriction Loss for Model Compression and Quantization—0
I3D: Transformer architectures with input-dependent dynamic depth for speech recognitionCode0
A Contrastive Knowledge Transfer Framework for Model Compression and Transfer LearningCode0
OTOV2: Automatic, Generic, User-Friendly—0
On Model Compression for Neural Networks: Framework, Algorithm, and Convergence GuaranteeCode0
Greener yet Powerful: Taming Large Code Generation Models with Quantization—0
Gradient-Free Structured Pruning with Unlabeled Data—0
Rotation Invariant Quantization for Model CompressionCode0
Adversarial Attacks on Machine Learning in Embedded and IoT Platforms—0
Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation—0
Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and UnderstandingCode1
Debiased Distillation by Transplanting the Last Layer—0
Show:102550
← PrevPage 11 of 28Next →
All datasetsImageNetQNLI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ADLIK-MO-ResNet50+W4A4Top-177.88—Unverified
2ADLIK-MO-ResNet50+W3A4Top-177.34—Unverified
3ResNet-18 + 4bit-1dim model compression using DKMTop-170.52—Unverified
4MobileNet-v1 + 4bit-1dim model compression using DKMTop-169.63—Unverified
5ResNet-18 + 2bit-1dim model compression using DKMTop-168.63—Unverified
6MobileNet-v1 + 2bit-1dim model compression using DKMTop-167.62—Unverified
7ResNet-18 + 4bit-4dim model compression using DKMTop-166.1—Unverified
8ResNet-18 + 2bit-2dim model compression using DKMTop-164.7—Unverified
9MobileNet-v1 + 4bit-4dim model compression using DKMTop-161.4—Unverified
10ResNet-18 + 1bit-1dim model compression using DKMTop-159.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MobileBERT + 2bit-1dim model compression using DKMAccuracy82.13—Unverified
2MobileBERT + 1bit-1dim model compression using DKMAccuracy63.17—Unverified