Deep Learning for Computer Vision
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization
Exploiting Transferable Knowledge for Fairness-aware Image Classification
Introspective Learning by Distilling Knowledge from Online Self-explanation
Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity
Meta-Learning with Context-Agnostic Initialisations
Second Order enhanced Multi-glimpse Attention in Visual Question Answering
Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
Unified Density-Aware Image Dehazing and Object Detection in Real-World Hazy Scenes
Part-aware Attention Network for Person Re-Identification
Image Captioning through Image Transformer
Feature Variance Ratio-Guided Channel Pruning for Deep Convolutional Network Acceleration
Learn more, forget less: Cues from human brain
Knowledge Transfer Graph for Deep Collaborative Learning
^Regularizing Meta-Learning via Gradient Dropout
Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks
Towards Optimal Filter Pruning with Balanced Performance and Pruning Speed
Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
Double Targeted Universal Adversarial Perturbations
Adversarially Robust Deep Image Super-Resolution using Entropy Regularization
Online Knowledge Distillation via Multi-branch Diversity Enhancement
Rotation Equivariant Orientation Estimation for Omnidirectional Localization
Contextual Semantic Interpretability
Few-Shot Object Detection by Second-order Pooling
Depth-Adapted CNN for RGB-D cameras
Generative Models for Computer Vision
Over-exposure Correction via Exposure and Scene Information Disentanglement
Novel-View Human Action Synthesis
Augmentation Network for Generalised Zero-Shot Learning
Local Facial Makeup Transfer via Disentangled Representation
^OpenGAN: Open Set Generative Adversarial Networks
CPTNet: Cascade Pose Transform Network for Single Image Talking Head Animation
TinyGAN: Distilling BigGAN for Conditional Image Generation
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
RF-GAN: A Light and Reconfigurable Network for Unpaired Image-to-Image Translation
GAN-based Noise Model for Denoising Real Images
Emotional Landscape Image Generation Using Generative Adversarial Networks
Feedback Recurrent Autoencoder for Video Compression
MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network
DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolution
dpVAEs: Fixing Sample Generation for Regularized VAEs
MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
EvolGAN: Evolutionary Generative Adversarial Networks
^Sequential View Synthesis with Transformer.