
-
SPAGAN: Shortest Path Graph Attention Network
Graph convolutional networks (GCN) have recently demonstrated their pote...
read it
-
Overcoming Catastrophic Forgetting in Graph Neural Networks
Catastrophic forgetting refers to the tendency that a neural network "fo...
read it
-
Progressive Network Grafting for Few-Shot Knowledge Distillation
Knowledge distillation has demonstrated encouraging performances in deep...
read it
-
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
Data mixing augmentation has proved effective in training deep models. R...
read it
-
Learning Propagation Rules for Attribution Map Generation
Prior gradient-based attribution-map methods rely on handcrafted propaga...
read it
-
Factorizable Graph Convolutional Networks
Graphs have been widely adopted to denote structural connections between...
read it
-
Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
State-of-the-art multi-object tracking (MOT) methods follow the tracking...
read it
-
Impression Space from Deep Template Network
It is an innate ability for humans to imagine something only according t...
read it
-
Disassembling Object Representations without Labels
In this paper, we study a new representation-learning task, which we ter...
read it
-
Learning Oracle Attention for High-fidelity Face Completion
High-fidelity face completion is a challenging task due to the rich and ...
read it
-
Distillating Knowledge from Graph Convolutional Networks
Existing knowledge distillation methods focus on convolutional neural ne...
read it
-
Distilling Knowledge from Graph Convolutional Networks
Existing knowledge distillation methods focus on convolutional neural ne...
read it
-
Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN
Recent advances in deep learning have provided procedures for learning o...
read it
-
DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
Exploring the intrinsic interconnections between the knowledge encoded i...
read it
-
Data-Free Adversarial Distillation
Knowledge Distillation (KD) has made remarkable progress in the last few...
read it
-
Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers
Lip reading has witnessed unparalleled development in recent years thank...
read it
-
Dynamic Instance Normalization for Arbitrary Style Transfer
Prior normalization methods rely on affine transformations to produce ar...
read it
-
Deep Model Transferability from Attribution Maps
Exploring the transferability between heterogeneous tasks sheds light on...
read it
-
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
A massive number of well-trained deep networks have been released by dev...
read it
-
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
An increasing number of well-trained deep networks have been released on...
read it
-
One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation
Class imbalance has been one of the major challenges for medical image s...
read it
-
Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers
Many well-trained Convolutional Neural Network(CNN) models have now been...
read it
-
Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Parts
Not all the human body parts have the same degree of freedom (DOF) due t...
read it
-
Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
In this paper, we investigate a novel deep-model reusing task. Our goal ...
read it
-
A Light Dual-Task Neural Network for Haze Removal
Single-image dehazing is a challenging problem due to its ill-posed natu...
read it
-
Amalgamating Knowledge towards Comprehensive Classification
With the rapid development of deep learning, there have been an unpreced...
read it
-
Wide Activation for Efficient and Accurate Image Super-Resolution
In this report we demonstrate that with same parameters and computationa...
read it
-
Dual Swap Disentangling
Learning interpretable disentangled representations is a crucial yet cha...
read it
-
Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks
Discriminative features are critical for machine learning applications. ...
read it
-
Horizontal Pyramid Matching for Person Re-identification
Despite the remarkable recent progress, person Re-identification (Re-ID)...
read it
-
Deep Motion Boundary Detection
Motion boundary detection is a crucial yet challenging problem. Prior me...
read it
-
FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification
Images captured by fisheye lenses violate the pinhole camera assumption ...
read it
-
A Performance Evaluation of Local Features for Image Based 3D Reconstruction
This paper performs a comprehensive and comparative evaluation of the st...
read it
-
Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids
In this paper, we propose gated recurrent feature pyramid for the proble...
read it
-
Globally Consistent Multi-People Tracking using Motion Patterns
Many state-of-the-art approaches to people tracking rely on detecting th...
read it
-
Do We Need Binary Features for 3D Reconstruction?
Binary features have been incrementally popular in the past few years du...
read it
-
Predicting People's 3D Poses from Short Sequences
We propose an efficient approach to exploiting motion information from c...
read it
-
Globally Optimal Cell Tracking using Integer Programming
We propose a novel approach to automatically tracking cell populations i...
read it