
-
GTA: Global Temporal Attention for Video Action Understanding
Self-attention learns pairwise interactions via dot products to model lo...
read it
-
Analyzing and Mitigating Compression Defects in Deep Learning
With the proliferation of deep learning methods, many computer vision pr...
read it
-
Intentonomy: a Dataset and Study towards Human Intent Understanding
An image is worth a thousand words, conveying information that goes beyo...
read it
-
Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
Graph Neural Networks (GNNs) are the predominant technique for learning ...
read it
-
What makes fake images detectable? Understanding properties that generalize
The quality of image generation and manipulation is reaching impressive ...
read it
-
PyTorch Metric Learning
Deep metric learning algorithms have a wide variety of applications, but...
read it
-
MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation
Semi-supervised domain adaptation (SSDA) aims to adapt models from a lab...
read it
-
Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
The performance of Multi-Source Unsupervised Domain Adaptation depends s...
read it
-
Neural Manifold Ordinary Differential Equations
To better conform to data geometry, recent deep generative modelling tec...
read it
-
Detecting Deep-Fake Videos from Appearance and Behavior
Synthetically-generated audios and videos – so-called deep fakes – conti...
read it
-
Quantization Guided JPEG Artifact Correction
The JPEG image compression algorithm is the most popular method of image...
read it
-
One-Shot Domain Adaptation For Face Generation
In this paper, we propose a framework capable of generating face images ...
read it
-
A Metric Learning Reality Check
Deep metric learning papers from the past four years have consistently c...
read it
-
Set-Structured Latent Representations
Unstructured data often has latent component structure, such as the obje...
read it
-
Deep Multi-Modal Sets
Many vision-related tasks benefit from reasoning over multiple modalitie...
read it
-
Differentiating through the Fréchet Mean
Recent advances in deep representation learning on Riemannian manifolds ...
read it
-
On Feature Normalization and Data Augmentation
Modern neural network training relies heavily on data augmentation for i...
read it
-
Measuring Dataset Granularity
Despite the increasing visibility of fine-grained recognition in our fie...
read it
-
Unconstrained Facial Expression Transfer using Style-based Generator
Facial expression transfer and reenactment has been an important researc...
read it
-
Fine-grained Synthesis of Unrestricted Adversarial Examples
We propose a novel approach for generating unrestricted adversarial exam...
read it
-
Unsupervised Deep Metric Learning via Auxiliary Rotation Loss
Deep metric learning is an important area due to its applicability to ma...
read it
-
Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
We present a systematic study of adversarial attacks on state-of-the-art...
read it
-
Cross-X Learning for Fine-Grained Visual Categorization
Recognizing objects from subcategories with very subtle differences rema...
read it
-
Enhancing Adversarial Example Transferability with an Intermediate Level Attack
Neural networks are vulnerable to adversarial examples, malicious inputs...
read it
-
An Analysis of Object Embeddings for Image Retrieval
We present an analysis of embeddings extracted from different pre-traine...
read it
-
Adversarial Example Decomposition
Research has shown that widely used deep neural networks are vulnerable ...
read it
-
Intermediate Level Adversarial Attack for Enhanced Transferability
Neural networks are vulnerable to adversarial examples, malicious inputs...
read it
-
DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
Harvesting dense pixel-level annotations to train deep neural networks f...
read it
-
Unsupervised Domain Adaptation for Semantic Segmentation with GANs
Visual Domain Adaptation is a problem of immense importance in computer ...
read it
-
Regularizing deep networks using efficient layerwise adversarial training
Adversarial training has been shown to regularize deep neural networks i...
read it
-
Self corrective Perturbations for Semantic Segmentation and Classification
Convolutional Neural Networks have been a subject of great importance ov...
read it
-
A Reinforcement Learning Approach to the View Planning Problem
We present a Reinforcement Learning (RL) solution to the view planning p...
read it