Search Results for author:
Found 17 papers, 8 papers with code
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image Classification
Semi-supervised image classification, leveraging pseudo supervision and consistency regularization, has demonstrated remarkable success.
RevColV2: Exploring Disentangled Representations in Masked Image Modeling
Such design enables our architecture with the nice property: maintaining disentangled low-level and semantic information at the end of the network in MIM pre-training.
Reversible Column Networks
Such architectural scheme attributes RevCol very different behavior from conventional networks: during forward propagation, features in RevCol are learned to be gradually disentangled when passing through each column, whose total information is maintained rather than compressed or discarded as other network does.
Ranked #8 on
Semantic Segmentation
on ADE20K
(using extra training data)
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further.
Ranked #2 on
Instance Segmentation
on COCO 2017 val
(AP metric)
ChemiRise: a data-driven retrosynthesis engine
We have developed an end-to-end, retrosynthesis system, named ChemiRise, that can propose complete retrosynthesis routes for organic compounds rapidly and reliably.
Representative Batch Normalization With Feature Calibration
We propose to add a simple yet effective feature calibration scheme into the centering and scaling operations of BatchNorm, enhancing the instance-specific representations with the negligible computational cost.
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window.
Molecular modeling with machine-learned universal potential functions
Molecular modeling is an important topic in drug discovery.
Global2Local: Efficient Structure Search for Video Action Segmentation
Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combination patterns further.
Ranked #20 on
Action Segmentation
on Breakfast
Delving Deep into Label Smoothing
Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets.
Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization
Learning to find an optimal mixed precision model that can preserve accuracy and satisfy the specific constraints on model size and computation is extremely challenge due to the difficult in training a mixed precision model and the huge space of all possible bit quantizations.
Dependency Aware Filter Pruning
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference.
Deep Hough Transform for Semantic Line Detection
In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task.
Ranked #2 on
Line Detection
on NKL
From Crowdsourcing to Crowdmining: Using Implicit Human Intelligence for Better Understanding of Crowdsourced Data
A generic model for CrowdMining is further proposed based on a set of existing studies.
GDRQ: Group-based Distribution Reshaping for Quantization
Low-bit quantization is challenging to maintain high performance with limited model capacity (e. g., 4-bit for both weights and activations).
Visualisation and Exploration of High-Dimensional Distributional Features in Lexical Semantic Classification
Vector space models and distributional information are widely used in NLP.
