Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Doretto, Gianfranco."'
Self-supervised learning (SSL) frameworks consist of pretext task, and loss function aiming to learn useful general features from unlabeled data. The basic idea of most SSL baselines revolves around enforcing the invariance to a variety of data augme
Externí odkaz:
http://arxiv.org/abs/2412.02896
Self Supervised learning (SSL) has demonstrated its effectiveness in feature learning from unlabeled data. Regarding this success, there have been some arguments on the role that mutual information plays within the SSL framework. Some works argued fo
Externí odkaz:
http://arxiv.org/abs/2412.02121
The success of self-supervised learning (SSL) has been the focus of multiple recent theoretical and empirical studies, including the role of data augmentation (in feature decoupling) as well as complete and dimensional representation collapse. While
Externí odkaz:
http://arxiv.org/abs/2412.02109
Efficient visual trackers overfit to their training distributions and lack generalization abilities, resulting in them performing well on their respective in-distribution (ID) test sets and not as well on out-of-distribution (OOD) sequences, imposing
Externí odkaz:
http://arxiv.org/abs/2411.18855
Autor:
Pham, Trong Thang, Ho, Ngoc-Vuong, Bui, Nhat-Tan, Phan, Thinh, Brijesh, Patel, Adjeroh, Donald, Doretto, Gianfranco, Nguyen, Anh, Wu, Carol C., Nguyen, Hien, Le, Ngan
Developing an interpretable system for generating reports in chest X-ray (CXR) analysis is becoming increasingly crucial in Computer-aided Diagnosis (CAD) systems, enabling radiologists to comprehend the decisions made by these systems. Despite the g
Externí odkaz:
http://arxiv.org/abs/2411.15413
Autor:
Habib, Al Zadid Sultan Bin, Wang, Kesheng, Hartley, Mary-Anne, Doretto, Gianfranco, Adjeroh, Donald A.
Effective analysis of tabular data still poses a significant problem in deep learning, mainly because features in tabular datasets are often heterogeneous and have different levels of relevance. This work introduces TabSeq, a novel framework for the
Externí odkaz:
http://arxiv.org/abs/2410.13203
This work addresses how to efficiently classify challenging histopathology images, such as gigapixel whole-slide images for cancer diagnostics with image-level annotation. We use images with annotated tumor regions to identify a set of tumor patches
Externí odkaz:
http://arxiv.org/abs/2409.13720
Microscopy data collections are becoming larger and more frequent. Accurate and precise quantitative analysis tools like cell instance segmentation are necessary to benefit from them. This is challenging due to the variability in the data, which requ
Externí odkaz:
http://arxiv.org/abs/2402.17165
Autor:
Farrelly, Colleen, Singh, Yashbir, Hathaway, Quincy A., Carlsson, Gunnar, Choudhary, Ashok, Paul, Rahul, Doretto, Gianfranco, Himeur, Yassine, Atalls, Shadi, Mansoor, Wathiq
Institutional bias can impact patient outcomes, educational attainment, and legal system navigation. Written records often reflect bias, and once bias is identified; it is possible to refer individuals for training to reduce bias. Many machine learni
Externí odkaz:
http://arxiv.org/abs/2311.13495
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot TAD method
Externí odkaz:
http://arxiv.org/abs/2311.00729