Browse > Methodology > Model Compression

Model Compression

27 papers with code ยท Methodology

State-of-the-art leaderboards

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Latest papers without code

Differentiable Mask Pruning for Neural Networks

10 Sep 2019

Most neural network models are large and require expensive computations to predict new instances.

MODEL COMPRESSION NEURAL ARCHITECTURE SEARCH

PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices

6 Sep 2019

Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method.

MODEL COMPRESSION

Knowledge Distillation for End-to-End Person Search

3 Sep 2019

We employ this to supervise the detector of our person search model at various levels using a specialized detector.

MODEL COMPRESSION OBJECT DETECTION PERSON SEARCH

Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation

27 Aug 2019

To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework for DNN applications.

MODEL COMPRESSION QUANTIZATION

On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression

27 Aug 2019

Despite their ubiquity in NLP tasks, Long Short-Term Memory (LSTM) networks suffer from computational inefficiencies caused by inherent unparallelizable recurrences, which further aggravates as LSTMs require more parameters for larger memory capacity.

MODEL COMPRESSION

Patient Knowledge Distillation for BERT Model Compression

25 Aug 2019

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks.

MODEL COMPRESSION

MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors

21 Aug 2019

In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR).

IMAGE RESTORATION MODEL COMPRESSION SUPER RESOLUTION

Tuning Algorithms and Generators for Efficient Edge Inference

31 Jul 2019

A surge in artificial intelligence and autonomous technologies have increased the demand toward enhanced edge-processing capabilities.

MODEL COMPRESSION

Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT

26 Jul 2019

Therefore, we propose Network of Neural Networks (NoNN), a new distributed IoT learning paradigm that compresses a large pretrained 'teacher' deep network into several disjoint and highly-compressed 'student' modules, without loss of accuracy.

IMAGE CLASSIFICATION MODEL COMPRESSION

Real-Time Correlation Tracking via Joint Model Compression and Transfer

23 Jul 2019

In the distillation process, we propose a fidelity loss to enable the student network to maintain the representation capability of the teacher network.

IMAGE CLASSIFICATION MODEL COMPRESSION OBJECT RECOGNITION VISUAL TRACKING