• Publications
  • Influence
Implicit Semantic Data Augmentation for Deep Networks
TLDR
This work shows that the proposed ISDA amounts to minimizing a novel robust CE loss, which adds negligible extra computational cost to a normal training procedure, and consistently improves the generalization performance of popular deep models (ResNets and DenseNets) on a variety of datasets. Expand
Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length
TLDR
This paper argues that every image has its own characteristics, and ideally the token number should be conditioned on each individual input, and proposes a Dynamic Transformer to automatically configure a proper number of tokens for each input image. Expand
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
TLDR
This work proposes a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning, which consistently improves the computational efficiency of a wide variety of deep models. Expand
Dynamic Neural Networks: A Survey
TLDR
This survey comprehensively review this rapidly developing area of dynamic networks by dividing dynamic networks into three main categories: sample-wise dynamic models that process each sample with data-dependent architectures or parameters; spatial-wiseynamic networks that conduct adaptive computation with respect to different spatial locations of image data; and temporal-wise Dynamic networks that perform adaptive inference along the temporal dimension for sequential data. Expand
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
TLDR
This paper addresses the issue of imbalance in real-world training data by augmenting minority classes with a recently proposed implicit semantic data augmentation (ISDA) algorithm, which produces diversified augmented samples by translating deep features along many semantically meaningful directions. Expand
Collaborative learning with corrupted labels
TLDR
This paper proposes a collaborative learning (co-learning) approach to improve the robustness and generalization performance of DNNs on datasets with corrupted labels by designing a deep network with two separate branches, coupled with a relabeling mechanism. Expand
Regularizing Deep Networks with Semantic Data Augmentation
TLDR
The proposed implicit semantic data augmentation (ISDA) first obtains semantically meaningful translations using an efficient sampling based method, and an upper bound of the expected cross-entropy loss on the augmented training set is derived, leading to a novel robust loss function. Expand
Logistics-aware manufacturing service collaboration optimisation towards industrial internet platform
TLDR
An adjacent matrix-based logistics-aware MS collaboration optimisation (LA-MSCO) model with detailed definitions of time, cost and reliability attributes of logistics is established and an improved artificial bee colony algorithm with both dimensional self-adaptation and group leader mechanisms, i.e. DSA-GL-ABC, is proposed for solving the LA- MSCO problem. Expand
Fault detection and isolation for Unmanned Aerial Vehicle sensors by using extended PMI filter
TLDR
This paper focuses on developing a method for detecting UAV sensor faults by using existing sensors, such as pitot tube, gyro, accelerometer and wind angle sensor, formulate the kinematics as a nonlinear state space system, which requires no dynamic information and thus is applicable to all aircraft. Expand
Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
TLDR
A novel meta-learning based SSL algorithm (Meta-Semi) that requires tuning only one additional hyper-parameter, compared with a standard supervised deep learning algorithm, to achieve competitive performance under various conditions of SSL. Expand
...
1
2
...