LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 7 of total 7

Search options

  1. Book ; Online: Exploring Visual Prompts for Adapting Large-Scale Models

    Bahng, Hyojin / Jahanian, Ali / Sankaranarayanan, Swami / Isola, Phillip

    2022  

    Abstract: We investigate the efficacy of visual prompting to adapt large-scale models in vision. Following the recent approach from prompt tuning and adversarial reprogramming, we learn a single image perturbation such that a frozen model prompted with this ... ...

    Abstract We investigate the efficacy of visual prompting to adapt large-scale models in vision. Following the recent approach from prompt tuning and adversarial reprogramming, we learn a single image perturbation such that a frozen model prompted with this perturbation performs a new task. Through comprehensive experiments, we demonstrate that visual prompting is particularly effective for CLIP and robust to distribution shift, achieving performance competitive with standard linear probes. We further analyze properties of the downstream dataset, prompt design, and output transformation in regard to adaptation performance. The surprising effectiveness of visual prompting provides a new perspective on adapting pre-trained models in vision. Code is available at http://hjbahng.github.io/visual_prompting .

    Comment: 16 pages, 10 figures
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Publishing date 2022-03-31
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: Aging with GRACE

    Hartvigsen, Thomas / Sankaranarayanan, Swami / Palangi, Hamid / Kim, Yoon / Ghassemi, Marzyeh

    Lifelong Model Editing with Discrete Key-Value Adaptors

    2022  

    Abstract: Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current model editors, ...

    Abstract Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current model editors, which modify such behaviors of pre-trained models, degrade model performance quickly across multiple, sequential edits. We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs. GRACE writes new mappings into a pre-trained model's latent space, creating a discrete, local codebook of edits without altering model weights. This is the first method enabling thousands of sequential edits using only streaming errors. Our experiments on T5, BERT, and GPT models show GRACE's state-of-the-art performance in making and retaining edits, while generalizing to unseen inputs. Our code is available at https://www.github.com/thartvigsen/grace}.

    Comment: Accepted to NeurIPS 2023
    Keywords Computer Science - Machine Learning
    Subject code 006
    Publishing date 2022-11-20
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Semantic uncertainty intervals for disentangled latent spaces

    Sankaranarayanan, Swami / Angelopoulos, Anastasios N. / Bates, Stephen / Romano, Yaniv / Isola, Phillip

    2022  

    Abstract: Meaningful uncertainty quantification in computer vision requires reasoning about semantic information -- say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow ... ...

    Abstract Meaningful uncertainty quantification in computer vision requires reasoning about semantic information -- say, the hair color of the person in a photo or the location of a car on the street. To this end, recent breakthroughs in generative modeling allow us to represent semantic information in disentangled latent spaces, but providing uncertainties on the semantic latent variables has remained challenging. In this work, we provide principled uncertainty intervals that are guaranteed to contain the true semantic factors for any underlying generative model. The method does the following: (1) it uses quantile regression to output a heuristic uncertainty interval for each element in the latent space (2) calibrates these uncertainties such that they contain the true value of the latent for a new, unseen input. The endpoints of these calibrated intervals can then be propagated through the generator to produce interpretable uncertainty visualizations for each semantic factor. This technique reliably communicates semantically meaningful, principled, and instance-adaptive uncertainty in inverse problems like image super-resolution and image completion.

    Comment: Accepted to NeurIPS 2022. Project page: https://swamiviv.github.io/semantic_uncertainty_intervals/
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence ; Computer Science - Machine Learning ; Statistics - Machine Learning
    Subject code 004
    Publishing date 2022-07-20
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: Social Trait Information in Deep Convolutional Neural Networks Trained for Face Identification.

    Parde, Connor J / Hu, Ying / Castillo, Carlos / Sankaranarayanan, Swami / O'Toole, Alice J

    Cognitive science

    2019  Volume 43, Issue 6, Page(s) e12729

    Abstract: Faces provide information about a person's identity, as well as their sex, age, and ethnicity. People also infer social and personality traits from the face - judgments that can have important societal and personal consequences. In recent years, deep ... ...

    Abstract Faces provide information about a person's identity, as well as their sex, age, and ethnicity. People also infer social and personality traits from the face - judgments that can have important societal and personal consequences. In recent years, deep convolutional neural networks (DCNNs) have proven adept at representing the identity of a face from images that vary widely in viewpoint, illumination, expression, and appearance. These algorithms are modeled on the primate visual cortex and consist of multiple processing layers of simulated neurons. Here, we examined whether a DCNN trained for face identification also retains a representation of the information in faces that supports social-trait inferences. Participants rated male and female faces on a diverse set of 18 personality traits. Linear classifiers were trained with cross validation to predict human-assigned trait ratings from the 512 dimensional representations of faces that emerged at the top-layer of a DCNN trained for face identification. The network was trained with 494,414 images of 10,575 identities and consisted of seven layers and 19.8 million parameters. The top-level DCNN features produced by the network predicted the human-assigned social trait profiles with good accuracy. Human-assigned ratings for the individual traits were also predicted accurately. We conclude that the face representations that emerge from DCNNs retain facial information that goes beyond the strict limits of their training.
    MeSH term(s) Algorithms ; Deep Learning ; Facial Recognition ; Humans ; Neural Networks, Computer ; Sociological Factors
    Language English
    Publishing date 2019-06-08
    Publishing country United States
    Document type Journal Article ; Research Support, U.S. Gov't, Non-P.H.S.
    ZDB-ID 2002940-8
    ISSN 1551-6709 ; 0364-0213
    ISSN (online) 1551-6709
    ISSN 0364-0213
    DOI 10.1111/cogs.12729
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  5. Book ; Online: Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion

    Tanno, Ryutaro / Saeedi, Ardavan / Sankaranarayanan, Swami / Alexander, Daniel C. / Silberman, Nathan

    2019  

    Abstract: The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying skill-levels ... ...

    Abstract The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying skill-levels and biases. Blindly treating these noisy labels as the ground truth limits the accuracy of learning algorithms in the presence of strong disagreement. This problem is critical for applications in domains such as medical imaging where both the annotation cost and inter-observer variability are high. In this work, we present a method for simultaneously learning the individual annotator model and the underlying true label distribution, using only noisy observations. Each annotator is modeled by a confusion matrix that is jointly estimated along with the classifier predictions. We propose to add a regularization term to the loss function that encourages convergence to the true annotator confusion matrix. We provide a theoretical argument as to how the regularization is essential to our approach both for the case of single annotator and multiple annotators. Despite the simplicity of the idea, experiments on image classification tasks with both simulated and real labels show that our method either outperforms or performs on par with the state-of-the-art methods and is capable of estimating the skills of annotators even with a single label available per image.

    Comment: 13 pages
    Keywords Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition ; Statistics - Machine Learning
    Subject code 006
    Publishing date 2019-02-10
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Book ; Online: Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition

    Ranjan, Rajeev / Bansal, Ankan / Xu, Hongyu / Sankaranarayanan, Swami / Chen, Jun-Cheng / Castillo, Carlos D. / Chellappa, Rama

    2018  

    Abstract: In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for subject ... ...

    Abstract In recent years, the performance of face verification and recognition systems based on deep convolutional neural networks (DCNNs) has significantly improved. A typical pipeline for face verification includes training a deep network for subject classification with softmax loss, using the penultimate layer output as the feature descriptor, and generating a cosine similarity score given a pair of face images or videos. The softmax loss function does not optimize the features to have higher similarity score for positive pairs and lower similarity score for negative pairs, which leads to a performance gap. In this paper, we propose a new loss function, called Crystal Loss, that restricts the features to lie on a hypersphere of a fixed radius. The loss can be easily implemented using existing deep learning frameworks. We show that integrating this simple step in the training pipeline significantly improves the performance of face verification and recognition systems. We achieve state-of-the-art performance for face verification and recognition on challenging LFW, IJB-A, IJB-B and IJB-C datasets over a large range of false alarm rates (10-1 to 10-7).

    Comment: Previously portions of this work appeared in arXiv:1703.09507, which was a conference version. This version is an extended journal version of it
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2018-04-03
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Article ; Online: Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms.

    Phillips, P Jonathon / Yates, Amy N / Hu, Ying / Hahn, Carina A / Noyes, Eilidh / Jackson, Kelsey / Cavazos, Jacqueline G / Jeckeln, Géraldine / Ranjan, Rajeev / Sankaranarayanan, Swami / Chen, Jun-Cheng / Castillo, Carlos D / Chellappa, Rama / White, David / O'Toole, Alice J

    Proceedings of the National Academy of Sciences of the United States of America

    2018  Volume 115, Issue 24, Page(s) 6171–6176

    Abstract: Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their ... ...

    Abstract Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accurate face identification: using people and/or machines working alone or in collaboration? In a comprehensive comparison of face identification by humans and computers, we found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test. Individual performance on the test varied widely. On the same test, four deep convolutional neural networks (DCNNs), developed between 2015 and 2017, identified faces within the range of human accuracy. Accuracy of the algorithms increased steadily over time, with the most recent DCNN scoring above the median of the forensic facial examiners. Using crowd-sourcing methods, we fused the judgments of multiple forensic facial examiners by averaging their rating-based identity judgments. Accuracy was substantially better for fused judgments than for individuals working alone. Fusion also served to stabilize performance, boosting the scores of lower-performing individuals and decreasing variability. Single forensic facial examiners fused with the best algorithm were more accurate than the combination of two examiners. Therefore, collaboration among humans and between humans and machines offers tangible benefits to face identification accuracy in important applications. These results offer an evidence-based roadmap for achieving the most accurate face identification possible.
    MeSH term(s) Algorithms ; Biometric Identification/methods ; Face/anatomy & histology ; Forensic Sciences/methods ; Humans ; Machine Learning ; Reproducibility of Results
    Language English
    Publishing date 2018-05-29
    Publishing country United States
    Document type Journal Article ; Research Support, Non-U.S. Gov't ; Research Support, U.S. Gov't, Non-P.H.S.
    ZDB-ID 209104-5
    ISSN 1091-6490 ; 0027-8424
    ISSN (online) 1091-6490
    ISSN 0027-8424
    DOI 10.1073/pnas.1721355115
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Cologne/Königswinter

    Zs.A 1148: Show issues Location:
    Je nach Verfügbarkeit (siehe Angabe bei Bestand)
    bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
    Jg. 1995 - 2021: Lesesall (1.OG)
    ab Jg. 2022: Lesesaal (EG)

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

To top