Results 1 to 10 of about 1,203,287 (165)
ROBUSTCAPS: A TRANSFORMATION-ROBUST CAPSULE NETWORK FOR IMAGE CLASSIFICATION [PDF]
ICTACT Journal on Image and Video Processing, 2023 Geometric transformations of the training data as well as the test data present challenges to the use of deep neural networks to vision-based learning tasks.
Sai Raam Venkataraman +2 more
doaj +1 more source
ICTACT Journal on Image and Video Processing, 2022 Transformation-robustness is an important feature for machine learning models that perform image classification. Many methods aim to bestow this property to models by the use of data augmentation strategies, while more formal guarantees are obtained via ...
Sai Raam Venkataraman +2 more
doaj +1 more source
EVALUATION OF LATTICE BASED XAI [PDF]
ICTACT Journal on Soft Computing, 2023 With multiple methods to extract explanations from a black box model, it becomes significant to evaluate the correctness of these Explainable AI (XAI) techniques themselves.
Bhaskaran Venkatsubramaniam +1 more
doaj +1 more source
BLOCKCHAIN ENABLED, COLLABORATIVE PLATFORM FOR AI AS A SERVICE [PDF]
ICTACT Journal on Soft Computing, 2023 With the advent of technology, modern human activities produce a huge amount of data. This vast amount of data facilitates a better model training, thus creating accurate predictions. But most of the business entities lack the facilities and resources to
Venkata Raghava Kurada +1 more
doaj +1 more source
XAI USING FORMAL CONCEPT LATTICE FOR IMAGE DATA [PDF]
ICTACT Journal on Image and Video Processing, 2023 A Formal concept lattice can be used to generate explanations from a black box model. This novel approach has been applied and proven for tabular data. It has also been compared to popular techniques in XAI.
Bhaskaran Venkatsubramaniam +1 more
doaj +1 more source
ACCURATE MOTION ESTIMATION FOR ROTATIONAL IMAGE SEQUENCES [PDF]
ICTACT Journal on Image and Video Processing, 2023 Complex motion patterns, non-rigid deformations, occlusions, and illumination changes largely affect rotational image sequences. This makes accurate motion estimation a challenging task.
Hirak Doshi, N Uday Kiran
doaj +1 more source
SSRN Electronic Journal, 2018 AbstractWe design a novel experiment to study how subjects update their beliefs about the beliefs of others. Three players receive sequential signals about an unknown state of the world. Player 1 reports her beliefs about the state; Player 2 simultaneously reports her beliefs about the beliefs of Player 1; Player 3 simultaneously reports her beliefs ...
Piotr Evdokimov, Umberto Garfagnini
openaire +2 more sources
CO-CURING NOISY ANNOTATIONS FOR FACIAL EXPRESSION RECOGNITION
ICTACT Journal on Image and Video Processing, 2021 Driven by the advancement in technology that can facilitate implementation of deep neural networks (DNNs), and due to the availability of large scale datasets, automatic recognition performance of the machines has increased by leaps and bounds.
Darshan Gera, S Balasubramanian
doaj +1 more source
ICTACT Journal on Image and Video Processing, 2021 Copyright protection of digital images is an important commercial requirement to individual artists and large organisations alike. Wavelet-based image watermarking methods have been in practice due to their robustness against standard geometrical and ...
Sai Shyam Sharma +1 more
doaj +1 more source
Scientific Reports, 2023 It is important but challenging for prospective health professionals to learn the visual distinction between potentially harmful and harmless skin lesions, such as malignant melanomas and benign nevi.
Nadja Beeler +3 more
doaj +1 more source