These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
SUBMIT A METRIC USE CASE
If you have a metric use case that you think should be featured in the Catalogue of Tools & Metrics for Trustworthy AI, we would love to hear from you!
SUBMITShrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Network
Interaction support/chatbotsRecognition/object detectionUploaded on Apr 22, 2024Multimodal Large Language Models (MLLMs) excel in generating responses based
on visual inputs. However, they often suffer from a bias towards generating
responses similar to their ...
Objective(s)
ProMISe: Promptable Medical Image Segmentation using SAM
Recognition/object detectionUploaded on Apr 22, 2024This paper introduces fourteen novel datasets for the evaluation of Large
Language Models' safety in the context of enterprise tasks. A method was
devised to evaluate a model's saf...
Objective(s)
Efficient Image Super-Resolution via Symmetric Visual Attention Network
Recognition/object detectionUploaded on Apr 22, 2024In this paper, we introduce an open-vocabulary panoptic segmentation model
that effectively unifies the strengths of the Segment Anything Model (SAM) with
the vision-language CLIP ...
Objective(s)
PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise
Interaction support/chatbotsRecognition/object detectionUploaded on Apr 2, 2024Multimodal Large Language Models (MLLMs) excel in generating responses based
on visual inputs. However, they often suffer from a bias towards generating
responses similar to their ...
Objective(s)
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
Recognition/object detectionUploaded on Apr 2, 2024Object detectors often perform poorly on data that differs from their
training set. Domain adaptive object detection (DAOD) methods have recently
demonstrated strong results on add...
Objective(s)
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
Recognition/object detectionUploaded on Nov 1, 2023We observe that despite their hierarchical convolutional nature, the
synthesis process of typical generative adversarial networks depends on
absolute pixel coordinates in an unheal...
Objective(s)
Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps
Recognition/object detectionUploaded on Nov 1, 2023Learning to reject unknown samples (not present in the source classes) in the
target domain is fairly important for unsupervised domain adaptation (UDA).
There exist two typical UD...
Objective(s)
UPANets: Learning from the Universal Pixel Attention Networks
Recognition/object detectionUploaded on Nov 1, 2023Diffusion frameworks have achieved comparable performance with previous
state-of-the-art image generation models. Researchers are curious about its
variants in discriminative tasks...
Objective(s)
TAPEX: Table Pre-training via Learning a Neural SQL Executor
Recognition/object detectionUploaded on Nov 1, 2023This paper presents a new framework for open-vocabulary semantic segmentation
with the pre-trained vision-language model, named Side Adapter Network (SAN).
Our approach models the ...
Objective(s)
Space-time Mixing Attention for Video Transformer
Recognition/object detectionUploaded on Nov 1, 2023The growing popularity of Vision Transformers as the go-to models for image
classification has led to an explosion of architectural modifications claiming
to be more efficient than...
Objective(s)
Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
Event/anomaly detectionRecognition/object detectionUploaded on Nov 1, 2023The design choices in the Transformer attention mechanism, including weak
inductive bias and quadratic computational complexity, have limited its
application for modeling long sequ...
Objective(s)
Self-attention Dual Embedding for Graphs with Heterophily
Recognition/object detectionUploaded on Nov 1, 20233D softwares are now capable of producing highly realistic images that look
nearly indistinguishable from the real images. This raises the question: can
real datasets be enhanced w...
Objective(s)
SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation
Forecasting/predictionUploaded on Nov 1, 2023During lung radiotherapy, the position of infrared reflective objects on the
chest can be recorded to estimate the tumor location. However, radiotherapy
systems have a latency inhe...
Objective(s)
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Event/anomaly detectionInteraction support/chatbotsUploaded on Nov 1, 2023Question answering (QA) is a fundamental means to facilitate assessment and
training of narrative comprehension skills for both machines and young
children, yet there is scarcity o...
Objective(s)
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Recognition/object detectionUploaded on Nov 1, 2023In this paper, we introduce a framework ARBEx, a novel attentive feature
extraction framework driven by Vision Transformer with reliability balancing to
cope against poor class dis...
Objective(s)
SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations
Recognition/object detectionUploaded on Nov 1, 2023Learning from complex real-life networks is a lively research area, with
recent advances in learning information-rich, low-dimensional network node
representations. However, state-...
Objective(s)
Rethinking Domain Generalization Baselines
Interaction support/chatbotsUploaded on Nov 1, 2023In this paper, we exploit the innate document segment structure for improving
the extractive summarization task. We build two text segmentation models and
find the most optimal str...
Objective(s)
Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
Recognition/object detectionUploaded on Nov 1, 2023Semi-supervised learning, i.e., training networks with both labeled and
unlabeled data, has made significant progress recently. However, existing works
have primarily focused on im...
Objective(s)
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
Reasoning with knowledge structures/planningRecognition/object detectionUploaded on Nov 1, 2023Recent powerful pre-trained language models have achieved remarkable
performance on most of the popular datasets for reading comprehension. It is
time to introduce more challenging...
Objective(s)
REGTR: End-to-end Point Cloud Correspondences with Transformers
Recognition/object detectionUploaded on Nov 1, 2023Methods based on convolutional neural networks have improved the performance
of biomedical image segmentation. However, most of these methods cannot
efficiently segment objects of ...
Objective(s)