Search Results - "Gong, Ruihao"
-
1
Forward and Backward Information Retention for Accurate Binary Neural Networks
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-01-2020)“…Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise…”
Get full text
Conference Proceeding -
2
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
Published in 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2019)“…Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of…”
Get full text
Conference Proceeding -
3
The Antimicrobial Peptide LJ-hep2 from Lateolabrax japonicus Exerting Activities against Multiple Pathogenic Bacteria and Immune Protection In Vivo
Published in Marine drugs (20-10-2022)“…Hepcidin is widely present in many kinds of fish and is an important innate immune factor. A variety of HAMP2-type hepcidins have strong antimicrobial activity…”
Get full text
Journal Article -
4
MgO coated P2-Na0.67Mn0.75Ni0.25O2 layered oxide cathode for Na-Ion batteries
Published in Journal of Power Sources Advances (01-01-2024)“…In this study, we propose an effective strategy to improve the electrochemical performance of a P2-Na0.67Mn0.75Ni0.25O2 (P2-MNO) cathode material for Na-ion…”
Get full text
Journal Article -
5
Anatase-Wrapped Rutile Nanorods as an Effective Electron Collector in Hybrid Photoanodes for Visible Light-Driven Oxygen Evolution
Published in Frontiers in chemistry (18-08-2021)“…Arrays of single crystal TiO rutile nanorods (RNRs) appear highly promising as electron-collecting substrates in hybrid photoanodes as the RNRs offer direct…”
Get full text
Journal Article -
6
Binary neural networks: A survey
Published in Pattern recognition (01-09-2020)“…•We summarize the binary neural network methods and categorize them into the naive binarization and the optimized binarization.•The binary neural networks are…”
Get full text
Journal Article -
7
Distribution-Sensitive Information Retention for Accurate Binary Neural Network
Published in International journal of computer vision (2023)“…Model binarization is an effective method of compressing neural networks and accelerating their inference process, which enables state-of-the-art models to run…”
Get full text
Journal Article -
8
Towards Unified INT8 Training for Convolutional Neural Network
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2020)“…Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with…”
Get full text
Conference Proceeding -
9
Diversifying Sample Generation for Accurate Data-Free Quantization
Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2021)“…Quantization has emerged as one of the most prevalent approaches to compress and accelerate neural networks. Recently, data-free quantization has been widely…”
Get full text
Conference Proceeding -
10
Rectify representation bias in vision-language models for long-tailed recognition
Published in Neural networks (01-04-2024)“…Natural data typically exhibits a long-tailed distribution, presenting great challenges for recognition tasks. Due to the extreme scarcity of training…”
Get full text
Journal Article -
11
Balanced Binary Neural Networks with Gated Residual
Published in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (01-05-2020)“…Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization,…”
Get full text
Conference Proceeding -
12
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
Published in 2021 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2021)“…User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven…”
Get full text
Conference Proceeding -
13
Self-Activation of a Polyoxometalate-Derived Composite Electrocatalyst for the Oxygen Evolution Reaction
Published in ACS applied energy materials (22-11-2021)“…The electrocatalytic oxygen evolution reaction (OER) is a key step to access “green hydrogen” by splitting water into O2 and H2. Here, we present a…”
Get full text
Journal Article -
14
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
Published in 2021 IEEE/CVF International Conference on Computer Vision (ICCV) (01-10-2021)“…Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly…”
Get full text
Conference Proceeding -
15
Annealing-based Label-Transfer Learning for Open World Object Detection
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2023)“…Open world object detection (OWOD) has attracted extensive attention due to its practicability in the real world. Previous OWOD works manually designed…”
Get full text
Conference Proceeding -
16
Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2023)“…Adversarial training has been demonstrated to be one of the most effective remedies for defending adversarial examples, yet it often suffers from the huge…”
Get full text
Conference Proceeding -
17
A Triad Photoanode for Visible Light‐Driven Water Oxidation via Immobilization of Molecular Polyoxometalate on Polymeric Carbon Nitride
Published in Advanced sustainable systems (Online) (01-05-2022)“…Due to their availability, low cost, nontoxicity, and tunability, polymeric carbon nitrides (CNx) represent one of the most attractive materials classes for…”
Get full text
Journal Article -
18
High-performance BiVO photoanodes: elucidating the combined effects of Mo-doping and modification with cobalt polyoxometalate
Published in Materials advances (05-06-2024)“…Bulk doping of BiVO 4 with molybdenum combined with surface modification with a cobalt polyoxometalate water oxidation catalyst (CoPOM = Na 10 [Co 4 (H 2 O) 2…”
Get full text
Journal Article -
19
Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2020)“…In this paper, we consider the low-bit quantization problem of face recognition (FR) under the open-set protocol. Different from well explored low-bit…”
Get full text
Conference Proceeding -
20
High-performance BiVO 4 photoanodes: elucidating the combined effects of Mo-doping and modification with cobalt polyoxometalate
Published in Materials advances (2024)“…Bulk doping of BiVO 4 with molybdenum combined with surface modification with a cobalt polyoxometalate water oxidation catalyst (CoPOM = Na 10 [Co 4 (H 2 O) 2…”
Get full text
Journal Article