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 501–525 of 1356 papers

TitleStatusHype
MobileNMT: Enabling Translation in 15MB and 30msCode1
Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation—0
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference—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
Show:102550
← PrevPage 21 of 55Next →
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