• Publications
  • Influence
Quantized Convolutional Neural Networks for Mobile Devices
TLDR
This paper proposes an efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Expand
Two-Step Quantization for Low-bit Neural Networks
TLDR
A simple yet effective Two-Step Quantization (TSQ) framework is proposed, by decomposing the network quantization problem into two steps: code learning and transformation function learning based on the learned codes, and the sparse quantization method for code learning. Expand
Recent advances in efficient computation of deep convolutional neural networks
TLDR
A comprehensive survey of recent advances in network acceleration, compression, and accelerator design from both algorithm and hardware points of view is provided. Expand
Semi-supervised Generative Adversarial Hashing for Image Retrieval
TLDR
This paper unify a generative model, a discriminative model and a deep hashing model in a framework for making use of triplet-wise information and unlabeled data, and proposes a semi-supervised ranking loss and an adversary ranking loss to learn binary codes which preserve semantic similarity for both labeled data and unl labeled data. Expand
Quantized CNN: A Unified Approach to Accelerate and Compress Convolutional Networks
TLDR
A quantized CNN is presented, a unified approach to accelerate and compress convolutional networks, guided by minimizing the approximation error of individual layer’s response, both fully connected and Convolutional layers are carefully quantized. Expand
From Hashing to CNNs: Training BinaryWeight Networks via Hashing
TLDR
The strong connection between inner-product preserving hashing and binary weight networks can be intrinsically regarded as a hashing problem, and an alternating optimization method to learn the hash codes instead of directly learning binary weights is proposed. Expand
Training Binary Weight Networks via Semi-Binary Decomposition
TLDR
A novel semi-binary decomposition method which decomposes a matrix into two binary matrices and a diagonal matrix, which shows that the proposed method can achieve \(\sim9\(\times \) speed-ups while reducing the consumption of on-chip memory and dedicated multipliers significantly. Expand
Pseudo Label based Unsupervised Deep Discriminative Hashing for Image Retrieval
TLDR
Experiments demonstrate that the proposed pseudo label based unsupervised deep discriminative hashing method outperforms the state-of-art unsuper supervised hashing methods. Expand
Learning Deep Features For MSR-bing Information Retrieval Challenge
TLDR
A CNN-based feature representation for visual recognition only using image-level information is proposed, which is pre-trained on a collection of clean datasets and fine-tuned on the bing datasets. Expand
Compact Global Descriptor for Neural Networks
TLDR
A generic family of lightweight global descriptors for modeling the interactions between positions across different dimensions that enables subsequent convolutions to access the informative global features with negligible computational complexity and parameters is presented. Expand
...
1
2
3
...