Search Results for author: Tal Hassner

Found 49 papers, 27 papers with code

HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings

no code implementations22 Dec 2023 Nikhil Mehta, Kevin J Liang, Jing Huang, Fu-Jen Chu, Li Yin, Tal Hassner

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

1 code implementation1 Dec 2023 Cuong N. Nguyen, Phong Tran, Lam Si Tung Ho, Vu Dinh, Anh T. Tran, Tal Hassner, Cuong V. Nguyen

We consider transferability estimation, the problem of estimating how well deep learning models transfer from a source to a target task.

regression Transfer Learning

On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms

no code implementations24 Oct 2023 Surbhi Mittal, Kartik Thakral, Richa Singh, Mayank Vatsa, Tamar Glaser, Cristian Canton Ferrer, Tal Hassner

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

1 code implementation CVPR 2023 Vishal Asnani, Xi Yin, Tal Hassner, Xiaoming Liu

Finally, we show that MaLP can be used as a discriminator for improving the generation quality of GMs.


You Only Need a Good Embeddings Extractor to Fix Spurious Correlations

no code implementations12 Dec 2022 Raghav Mehta, Vítor Albiero, Li Chen, Ivan Evtimov, Tamar Glaser, Zhiheng Li, Tal Hassner

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

1 code implementation CVPR 2023 Zhiheng Li, Ivan Evtimov, Albert Gordo, Caner Hazirbas, Tal Hassner, Cristian Canton Ferrer, Chenliang Xu, Mark Ibrahim

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.

Domain Generalization Image Classification +1

GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction

1 code implementation24 Oct 2022 Samrudhdhi B Rangrej, Kevin J Liang, Tal Hassner, James J Clark

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.

Action Recognition

Task Grouping for Multilingual Text Recognition

1 code implementation13 Oct 2022 Jing Huang, Kevin J Liang, Rama Kovvuri, Tal Hassner

Most existing OCR methods focus on alphanumeric characters due to the popularity of English and numbers, as well as their corresponding datasets.

Optical Character Recognition (OCR)

Generalization Bounds for Deep Transfer Learning Using Majority Predictor Accuracy

no code implementations13 Sep 2022 Cuong N. Nguyen, Lam Si Tung Ho, Vu Dinh, Tal Hassner, Cuong V. Nguyen

We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task.

Generalization Bounds Transfer Learning

Few-shot Learning with Noisy Labels

1 code implementation CVPR 2022 Kevin J Liang, Samrudhdhi B. Rangrej, Vladan Petrovic, Tal Hassner

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.

Few-Shot Learning Learning with noisy labels

Proactive Image Manipulation Detection

1 code implementation CVPR 2022 Vishal Asnani, Xi Yin, Tal Hassner, Sijia Liu, Xiaoming Liu

That is, a template protected real image, and its manipulated version, is better discriminated compared to the original real image vs. its manipulated one.

Image Manipulation Image Manipulation Detection

FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment

no code implementations25 Feb 2022 Yuval Nirkin, Yosi Keller, Tal Hassner

Unlike previous work, we offer a subject agnostic swapping scheme that can be applied to pairs of faces without requiring training on those faces.

Face Reenactment Face Swapping +1

Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection

1 code implementation NeurIPS 2021 Koby Bibas, Meir Feder, Tal Hassner

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

Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images

1 code implementation15 Jun 2021 Vishal Asnani, Xi Yin, Tal Hassner, Xiaoming Liu

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.

DeepFake Detection Face Swapping

TextStyleBrush: Transfer of Text Aesthetics from a Single Example

1 code implementation15 Jun 2021 Praveen Krishnan, Rama Kovvuri, Guan Pang, Boris Vassilev, Tal Hassner

We present a novel approach for disentangling the content of a text image from all aspects of its appearance.


TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

no code implementations CVPR 2021 Amanpreet Singh, Guan Pang, Mandy Toh, Jing Huang, Wojciech Galuba, Tal Hassner

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

1 code implementation CVPR 2021 Jing Huang, Guan Pang, Rama Kovvuri, Mandy Toh, Kevin J Liang, Praveen Krishnan, Xi Yin, Tal Hassner

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.

Optical Character Recognition (OCR) Text Detection

HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation

1 code implementation CVPR 2021 Yuval Nirkin, Lior Wolf, Tal Hassner

We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder.

Decoder Dichotomous Image Segmentation +2

img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

2 code implementations CVPR 2021 Vítor Albiero, Xingyu Chen, Xi Yin, Guan Pang, Tal Hassner

Tests on AFLW2000-3D and BIWI show that our method runs at real-time and outperforms state of the art (SotA) face pose estimators.

3D Face Alignment Face Alignment +3

DeepFake Detection Based on the Discrepancy Between the Face and its Context

no code implementations27 Aug 2020 Yuval Nirkin, Lior Wolf, Yosi Keller, Tal Hassner

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).

DeepFake Detection Face Identification +2

Balancing Specialization, Generalization, and Compression for Detection and Tracking

no code implementations25 Sep 2019 Dotan Kaufman, Koby Bibas, Eran Borenstein, Michael Chertok, Tal Hassner

To this end, we propose a novel loss that balances compression and acceleration of a deep learning model vs. loss of generalization capabilities.

Model Compression

Transferability and Hardness of Supervised Classification Tasks

no code implementations ICCV 2019 Anh T. Tran, Cuong V. Nguyen, Tal Hassner

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.

Attribute Classification +2

Toward Understanding Catastrophic Forgetting in Continual Learning

no code implementations2 Aug 2019 Cuong V. Nguyen, Alessandro Achille, Michael Lam, Tal Hassner, Vijay Mahadevan, Stefano Soatto

As an application, we apply our procedure to study two properties of a task sequence: (1) total complexity and (2) sequential heterogeneity.

Continual Learning

ExpNet: Landmark-Free, Deep, 3D Facial Expressions

1 code implementation2 Feb 2018 Feng-Ju Chang, Anh Tuan Tran, Tal Hassner, Iacopo Masi, Ram Nevatia, Gerard Medioni

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)

3D Face Reconstruction 3D Facial Expression Recognition +2

Extreme 3D Face Reconstruction: Seeing Through Occlusions

1 code implementation CVPR 2018 Anh Tuan Tran, Tal Hassner, Iacopo Masi, Eran Paz, Yuval Nirkin, Gerard Medioni

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).

3D Face Reconstruction Decoder

FacePoseNet: Making a Case for Landmark-Free Face Alignment

6 code implementations24 Aug 2017 Feng-Ju Chang, Anh Tuan Tran, Tal Hassner, Iacopo Masi, Ram Nevatia, Gerard Medioni

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)

3D Face Alignment Face Alignment +4

On Face Segmentation, Face Swapping, and Face Perception

2 code implementations22 Apr 2017 Yuval Nirkin, Iacopo Masi, Anh Tuan Tran, Tal Hassner, Gerard Medioni

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.

Face Swapping

Temporal Tessellation: A Unified Approach for Video Analysis

1 code implementation ICCV 2017 Dotan Kaufman, Gil Levi, Tal Hassner, Lior Wolf

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.

Action Detection Video Captioning +2

The CUDA LATCH Binary Descriptor: Because Sometimes Faster Means Better

4 code implementations13 Sep 2016 Christopher Parker, Matthew Daiter, Kareem Omar, Gil Levi, Tal Hassner

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.

Face Recognition Using Deep Multi-Pose Representations

no code implementations23 Mar 2016 Wael Abd-Almageed, Yue Wua, Stephen Rawlsa, Shai Harel, Tal Hassner, Iacopo Masi, Jongmoo Choi, Jatuporn Toy Leksut, Jungyeon Kim, Prem Natarajan, Ram Nevatia, Gerard Medioni

In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features.

Face Recognition Face Verification +1

GPU-Based Computation of 2D Least Median of Squares with Applications to Fast and Robust Line Detection

1 code implementation5 Oct 2015 Gil Shapira, Tal Hassner

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.

Line Detection

Wide baseline stereo matching with convex bounded-distortion constraints

no code implementations10 Jun 2015 Meirav Galun, Tal Amir, Tal Hassner, Ronen Basri, Yaron Lipman

This paper focuses on the challenging problem of finding correspondences once approximate epipolar constraints are given.

Stereo Matching Stereo Matching Hand

LATCH: Learned Arrangements of Three Patch Codes

5 code implementations15 Jan 2015 Gil Levi, Tal Hassner

In order to provide more robustness, we instead propose a novel means of comparing pixel patches.

Effective Face Frontalization in Unconstrained Images

no code implementations CVPR 2015 Tal Hassner, Shai Harel, Eran Paz, Roee Enbar

"Frontalization" is the process of synthesizing frontal facing views of faces appearing in single unconstrained photos.

Face Recognition

Dense Correspondences Across Scenes and Scales

no code implementations24 Jun 2014 Moria Tau, Tal Hassner

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

no code implementations14 Apr 2013 Tal Hassner, Ronen Basri

The known depths of the selected database objects act as shape priors which constrain the process of estimating the object's depth.

Depth Estimation Object

Cannot find the paper you are looking for? You can Submit a new open access paper.