Search Results for author:
Found 49 papers, 27 papers with code
HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings
Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Simple Transferability Estimation for Regression Tasks
We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task.
On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms
However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development.
MaLP: Manipulation Localization Using a Proactive Scheme
Finally, we show that MaLP can be used as a discriminator for improving the generation quality of GMs.
Self-Supervised Object Detection from Egocentric Videos
Understanding the visual world from the perspective of humans (egocentric) has been a long-standing challenge in computer vision.
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
With experiments on a wide range of pre-trained models and pre-training datasets, we show that the capacity of the pre-training model and the size of the pre-training dataset matters.
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Key to advancing the reliability of vision systems is understanding whether existing methods can overcome multiple shortcuts or struggle in a Whac-A-Mole game, i. e., where mitigating one shortcut amplifies reliance on others.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction
Many online action prediction models observe complete frames to locate and attend to informative subregions in the frames called glimpses and recognize an ongoing action based on global and local information.
Task Grouping for Multilingual Text Recognition
Most existing OCR methods focus on alphanumeric characters due to the popularity of English and numbers, as well as their corresponding datasets.
Generalization Bounds for Deep Transfer Learning Using Majority Predictor Accuracy
We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task.
Few-shot Learning with Noisy Labels
Our results show that TraNFS is on-par with leading FSL methods on clean support sets, yet outperforms them, by far, in the presence of label noise.
Proactive Image Manipulation Detection
That is, a template protected real image, and its manipulated version, is better discriminated compared to the original real image vs. its manipulated one.
FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment
Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training on those faces.
Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection
Furthermore, we describe how to efficiently apply the derived pNML regret to any pretrained deep NN, by employing the explicit pNML for the last layer, followed by the softmax function.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Revisiting Linear Decision Boundaries for Few-Shot Learning with Transformer Hypernetworks
Few-shot learning (FSL) methods aim to generalize a model to new unseen classes using only a small number of support examples.
TextStyleBrush: Transfer of Text Aesthetics from a Single Example
We present a novel approach for disentangling the content of a text image from all aspects of its appearance.
Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
To tackle this problem, we propose a framework with two components: a Fingerprint Estimation Network (FEN), which estimates a GM fingerprint from a generated image by training with four constraints to encourage the fingerprint to have desired properties, and a Parsing Network (PN), which predicts network architecture and loss functions from the estimated fingerprints.
TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text
A crucial component for the scene text based reasoning required for TextVQA and TextCaps datasets involve detecting and recognizing text present in the images using an optical character recognition (OCR) system.
Optical Character Recognition
Optical Character Recognition (OCR)
+2
A Multiplexed Network for End-to-End, Multilingual OCR
Recent advances in OCR have shown that an end-to-end (E2E) training pipeline that includes both detection and recognition leads to the best results.
HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder.
Ranked #5 on
Dichotomous Image Segmentation
on DIS-TE1
Dichotomous Image Segmentation
Real-Time Semantic Segmentation
+1
img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation
Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators.
Ranked #6 on
Head Pose Estimation
on BIWI
DeepFake Detection Based on the Discrepancy Between the Face and its Context
Our approach involves two networks: (i) a face identification network that considers the face region bounded by a tight semantic segmentation, and (ii) a context recognition network that considers the face context (e. g., hair, ears, neck).
Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
Recent end-to-end trainable methods for scene text spotting, integrating detection and recognition, showed much progress.
Ranked #11 on
Text Spotting
on Total-Text
LEEP: A New Measure to Evaluate Transferability of Learned Representations
We introduce a new measure to evaluate the transferability of representations learned by classifiers.
Ranked #4 on
Transferability
on classification benchmark
Balancing Specialization, Generalization, and Compression for Detection and Tracking
To this end, we propose a novel loss that balances compression and acceleration of a deep learning model vs. loss of generalization capabilities.
Transferability and Hardness of Supervised Classification Tasks
As a case study, we transfer a learned face recognition model to CelebA attribute classification tasks, showing state of the art accuracy for tasks estimated to be highly transferable.
FSGAN: Subject Agnostic Face Swapping and Reenactment
We present Face Swapping GAN (FSGAN) for face swapping and reenactment.
Toward Understanding Catastrophic Forgetting in Continual Learning
As an application, we apply our procedure to study two properties of a task sequence: (1) total complexity and (2) sequential heterogeneity.
Learn Stereo, Infer Mono: Siamese Networks for Self-Supervised, Monocular, Depth Estimation
The field of self-supervised monocular depth estimation has seen huge advancements in recent years.
Ranked #53 on
Monocular Depth Estimation
on KITTI Eigen split
Precise Detection in Densely Packed Scenes
We propose a novel, deep-learning based method for precise object detection, designed for such challenging settings.
Ranked #4 on
Dense Object Detection
on SKU-110K
ExpNet: Landmark-Free, Deep, 3D Facial Expressions
Our ExpNet CNN is applied directly to the intensities of a face image and regresses a 29D vector of 3D expression coefficients.
Ranked #1 on
3D Facial Expression Recognition
on 2017_test set
(using extra training data)
Extreme 3D Face Reconstruction: Seeing Through Occlusions
Motivated by the concept of bump mapping, we propose a layered approach which decouples estimation of a global shape from its mid-level details (e. g., wrinkles).
FacePoseNet: Making a Case for Landmark-Free Face Alignment
Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method.
Ranked #1 on
Facial Landmark Detection
on 300W
(Mean Error Rate metric)
On Face Segmentation, Face Swapping, and Face Perception
To this end, we use the Labeled Faces in the Wild (LFW) benchmark and measure the effect of intra- and inter-subject face swapping on recognition.
Temporal Tessellation: A Unified Approach for Video Analysis
A test video is processed by forming correspondences between its clips and the clips of reference videos with known semantics, following which, reference semantics can be transferred to the test video.
Ranked #38 on
Video Retrieval
on MSR-VTT
Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
The 3D shapes of faces are well known to be discriminative.
Ranked #4 on
3D Face Reconstruction
on Florence
(Average 3D Error metric)
The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better
Our results show that CLATCH provides high quality 3D reconstructions at fractions of the time required by other representations, with little, if any, loss of reconstruction quality.
Pooling Faces: Template based Face Recognition with Pooled Face Images
We propose a novel approach to template based face recognition.
Face Recognition Using Deep Multi-Pose Representations
In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features.
Ranked #14 on
Face Verification
on IJB-A
Do We Really Need to Collect Millions of Faces for Effective Face Recognition?
Face recognition capabilities have recently made extraordinary leaps.
Ranked #12 on
Face Verification
on IJB-A
Wide Baseline Stereo Matching With Convex Bounded Distortion Constraints
This paper focuses on the challenging problem of finding correspondences once approximate epipolar constraints are given.
Facial Landmark Detection with Tweaked Convolutional Neural Networks
We present a novel convolutional neural network (CNN) design for facial landmark coordinate regression.
Age and Gender Classification using Convolutional Neural Networks
Automatic age and gender classification has become relevant to an increasing amount of applications, particularly since the rise of social platforms and social media.
Ranked #6 on
Age And Gender Classification
on Adience Gender
GPU-Based Computation of 2D Least Median of Squares with Applications to Fast and Robust Line Detection
The 2D Least Median of Squares (LMS) is a popular tool in robust regression because of its high breakdown point: up to half of the input data can be contaminated with outliers without affecting the accuracy of the LMS estimator.
Wide baseline stereo matching with convex bounded-distortion constraints
This paper focuses on the challenging problem of finding correspondences once approximate epipolar constraints are given.
LATCH: Learned Arrangements of Three Patch Codes
In order to provide more robustness, we instead propose a novel means of comparing pixel patches.
Effective Face Frontalization in Unconstrained Images
"Frontalization" is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos.
Dense Correspondences Across Scenes and Scales
Doing so allows scale invariant descriptors to be extracted anywhere in the image, not just in detected interest points.
Single View Depth Estimation from Examples
The known depths of the selected database objects act as shape priors which constrain the process of estimating the object's depth.
