TAR
33 papers with code • 0 benchmarks • 1 datasets
Technology Assisted Review
Benchmarks
These leaderboards are used to track progress in TAR
CLEF-TAR
Most implemented papers
Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answering
We then used this dataset to train Spanish QA systems by fine-tuning a Multilingual-BERT model.
On the Intrinsic Dimensionality of Image Representations
ansuini/IntrinsicDimDeep
•
•
CVPR 2019
This paper addresses the following questions pertaining to the intrinsic dimensionality of any given image representation: (i) estimate its intrinsic dimensionality, (ii) develop a deep neural network based non-linear mapping, dubbed DeepMDS, that transforms the ambient representation to the minimal intrinsic space, and (iii) validate the veracity of the mapping through image matching in the intrinsic space.
Tamper-Resistant Safeguards for Open-Weight LLMs
rishub-tamirisa/tamper-resistance
•
•
Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use.
DocFace: Matching ID Document Photos to Selfies
seasonSH/DocFace
•
•
Numerous activities in our daily life, including transactions, access to services and transportation, require us to verify who we are by showing our ID documents containing face images, e. g. passports and driver licenses.
Tangent-Normal Adversarial Regularization for Semi-supervised Learning
uuujf/TNAR
•
•
CVPR 2019
The proposed TNAR is composed by two complementary parts, the tangent adversarial regularization (TAR) and the normal adversarial regularization (NAR).
DocFace+: ID Document to Selfie Matching
seasonSH/DocFace
•
•
Numerous activities in our daily life require us to verify who we are by showing our ID documents containing face images, such as passports and driver licenses, to human operators.
Infant-Prints: Fingerprints for Reducing Infant Mortality
In developing countries around the world, a multitude of infants continue to suffer and die from vaccine-preventable diseases, and malnutrition.
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
EdwinKim3069/XtarNet
•
•
ICML 2020
The base and novel classifiers quickly adapt to a given task by utilizing the TAR.
Infant-ID: Fingerprints for Global Good
In many of the least developed and developing countries, a multitude of infants continue to suffer and die from vaccine-preventable diseases and malnutrition.
Incorporating a Local Translation Mechanism into Non-autoregressive Translation
shawnkx/NAT-with-Local-AT
•
•
EMNLP 2020
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs.
