Papers Model Compression
“Model Compression” 태그가 달린 논문 1,632편 · 필터 해제
HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble
Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemble training method explores different tr…
DiversityEnsemble LearningModel CompressionQuantizationOne-Shot Model for Mixed-Precision Quantization
Neural network quantization is a popular approach for model compression. Modern hardware supports quantization in mixed-precision mode, which allows for greater compression rates but adds the challenging task of sear…
modelModel CompressionQuantizationSuper-ResolutionDistilling Focal Knowledge From Imperfect Expert for 3D Object Detection
Multi-camera 3D object detection blossoms in recent years and most of state-of-the-art methods are built up on the bird's-eye-view (BEV) representations. Albeit remarkable performance, these works suffer from low eff…
3D geometry3D Object DetectionKnowledge DistillationModel Compression+2Compression-Aware Video Super-Resolution
Videos stored on mobile devices or delivered on the Internet are usually in compressed format and are of various unknown compression parameters, but most video super-resolution (VSR) methods often assume ideal inputs…
Model CompressionSuper-ResolutionVideo EnhancementVideo Super-ResolutionMemory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis
Scalable deep Super-Resolution (SR) models are increasingly in demand, whose memory can be customized and tuned to the computational recourse of the platform. The existing dynamic scalable SR methods are not memory-f…
image-classificationImage ClassificationModel CompressionSuper-ResolutionICD-Face: Intra-class Compactness Distillation for Face Recognition
Knowledge distillation is an effective model compression method to improve the performance of a lightweight student model by transferring the knowledge of a well-performed teacher model, which has been widely adopted…
Face RecognitionKnowledge DistillationModel CompressionSSDA: Secure Source-Free Domain Adaptation
Source-free domain adaptation (SFDA) is a popular unsupervised domain adaptation method where a pre-trained model from a source domain is adapted to a target domain without accessing any source data. Despite rich res…
Backdoor AttackDomain AdaptationModel CompressionSource-Free Domain Adaptation+2Tiny Updater: Towards Efficient Neural Network-Driven Software Updating
Significant advancements have been accomplished with deep neural networks in diverse visual tasks, which have substantially elevated their deployment in edge device software. However, during the update of neural netw…
Efficient Neural Networkimage-classificationImage ClassificationImage-to-Image Translation+3FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks
Model compression via quantization and sparsity enhancement has gained an immense interest to enable the deployment of deep neural networks (DNNs) in resource-constrained edge environments. Although these techniques have…
Model CompressionQuantizationBD-KD: Balancing the Divergences for Online Knowledge Distillation
We address the challenge of producing trustworthy and accurate compact models for edge devices. While Knowledge Distillation (KD) has improved model compression in terms of achieving high accuracy performance, calibratio…
Knowledge DistillationModel CompressionTransfer LearningFFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos
Neural fields, also known as coordinate-based or implicit neural representations, have shown a remarkable capability of representing, generating, and manipulating various forms of signals. For video representations, howe…
Model CompressionQuantizationVideo CompressionVideo ReconstructionSpike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task
Spiking Neural Networks (SNNs), known for their potential to enable low energy consumption and computational cost, can bring significant advantages to the realm of embedded machine learning for edge applications. However…
Model CompressionTransfer LearningFSCNN: A Fast Sparse Convolution Neural Network Inference System
Convolution neural networks (CNNs) have achieved remarkable success, but typically accompany high computation cost and numerous redundant weight parameters. To reduce the FLOPs, structure pruning is a popular approach to…
Model CompressionSwing Distillation: A Privacy-Preserving Knowledge Distillation Framework
Knowledge distillation (KD) has been widely used for model compression and knowledge transfer. Typically, a big teacher model trained on sufficient data transfers knowledge to a small student model. However, despite the …
Knowledge DistillationModel CompressionPrivacy PreservingTransfer LearningCan We Find Strong Lottery Tickets in Generative Models?
Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update. Neural network pruning is considered the main cornerston…
Model CompressionNetwork PruningRepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently, several PTQ schemes for vision transform…
Model CompressionQuantizationEfficient Speech Representation Learning with Low-Bit Quantization
With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investig…
Model CompressionQuantizationRepresentation LearningSpeech Representation LearningError-aware Quantization through Noise Tempering
Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model …
Model CompressionQuantizationLeveraging Different Learning Styles for Improved Knowledge Distillation in Biomedical Imaging
Learning style refers to a type of training mechanism adopted by an individual to gain new knowledge. As suggested by the VARK model, humans have different learning preferences, like Visual (V), Auditory (A), Read/Write …
Knowledge DistillationModel CompressionFedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street Views
Federated Deep Learning frameworks can be used strategically to monitor Land Use locally and infer environmental impacts globally. Distributed data from across the world would be needed to build a global model for Land U…
Knowledge DistillationModel CompressionSemantic Segmentation