اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدComputer Vision and Conflicting Values: Describing People with Automated Alt Text
360
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Scholars have recently drawn attention to a range of controversial issues posed by the use of computer vision for automatically generating descriptions of people in images. Despite these concerns, automated image description has become an important tool to ensure equitable access to information for blind and low vision people. In this paper, we investigate the ethical dilemmas faced by companies that have adopted the use of computer vision for producing alt text: textual descriptions of images for blind and low vision people, We use Facebooks automatic alt text tool as our primary case study. First, we analyze the policies that Facebook has adopted with respect to identity categories, such as race, gender, age, etc., and the companys decisions about whether to present these terms in alt text. We then describe an alternative -- and manual -- approach practiced in the museum community, focusing on how museums determine what to include in alt text descriptions of cultural artifacts. We compare these policies, using notable points of contrast to develop an analytic framework that characterizes the particular apprehensions behind these policy choices. We conclude by considering two strategies that seem to sidestep some of these concerns, finding that there are no easy ways to avoid the normative dilemmas posed by the use of computer vision to automate alt text.
قيم البحث
اقرأ أيضاً
Existing methods for vision-and-language learning typically require designing task-specific architectures and objectives for each task. For example, a multi-label answer classifier for visual question answering, a region scorer for referring expressi
on comprehension, and a language decoder for image captioning, etc. To alleviate these hassles, in this work, we propose a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation, where our models learn to generate labels in text based on the visual and textual inputs. On 7 popular vision-and-language benchmarks, including visual question answering, referring expression comprehension, visual commonsense reasoning, most of which have been previously modeled as discriminative tasks, our generative approach (with a single unified architecture) reaches comparable performance to recent task-specific state-of-the-art vision-and-language models. Moreover, our generative approach shows better generalization ability on questions that have rare answers. Also, we show that our framework allows multi-task learning in a single architecture with a single set of parameters, achieving similar performance to separately optimized single-task models. Our code is publicly available at: https://github.com/j-min/VL-T5
One of the most challenging topics in Natural Language Processing (NLP) is visually-grounded language understanding and reasoning. Outdoor vision-and-language navigation (VLN) is such a task where an agent follows natural language instructions and na
vigates a real-life urban environment. Due to the lack of human-annotated instructions that illustrate intricate urban scenes, outdoor VLN remains a challenging task to solve. This paper introduces a Multimodal Text Style Transfer (MTST) learning approach and leverages external multimodal resources to mitigate data scarcity in outdoor navigation tasks. We first enrich the navigation data by transferring the style of the instructions generated by Google Maps API, then pre-train the navigator with the augmented external outdoor navigation dataset. Experimental results show that our MTST learning approach is model-agnostic, and our MTST approach significantly outperforms the baseline models on the outdoor VLN task, improving task completion rate by 8.7% relatively on the test set.
A core problem in cognitive science and machine learning is to understand how humans derive semantic representations from perceptual objects, such as color from an apple, pleasantness from a musical chord, or seriousness from a face. Markov Chain Mon
te Carlo with People (MCMCP) is a prominent method for studying such representations, in which participants are presented with binary choice trials constructed such that the decisions follow a Markov Chain Monte Carlo acceptance rule. However, while MCMCP has strong asymptotic properties, its binary choice paradigm generates relatively little information per trial, and its local proposal function makes it slow to explore the parameter space and find the modes of the distribution. Here we therefore generalize MCMCP to a continuous-sampling paradigm, where in each iteration the participant uses a slider to continuously manipulate a single stimulus dimension to optimize a given criterion such as pleasantness. We formulate both methods from a utility-theory perspective, and show that the new method can be interpreted as Gibbs Sampling with People (GSP). Further, we introduce an aggregation parameter to the transition step, and show that this parameter can be manipulated to flexibly shift between Gibbs sampling and deterministic optimization. In an initial study, we show GSP clearly outperforming MCMCP; we then show that GSP provides novel and interpretable results in three other domains, namely musical chords, vocal emotions, and faces. We validate these results through large-scale perceptual rating experiments. The final experiments use GSP to navigate the latent space of a state-of-the-art image synthesis network (StyleGAN), a promising approach for applying GSP to high-dimensional perceptual spaces. We conclude by discussing future cognitive applications and ethical implications.
Forthcoming surveys such as the Large Synoptic Survey Telescope (LSST) and Euclid necessitate automatic and efficient identification methods of strong lensing systems. We present a strong lensing identification approach that utilizes a feature extrac
tion method from computer vision, the Histogram of Oriented Gradients (HOG), to capture edge patterns of arcs. We train a supervised classifier model on the HOG of mock strong galaxy-galaxy lens images similar to observations from the Hubble Space Telescope (HST) and LSST. We assess model performance with the area under the curve (AUC) of a Receiver Operating Characteristic (ROC) curve. Models trained on 10,000 lens and non-lens containing images images exhibit an AUC of 0.975 for an HST-like sample, 0.625 for one exposure of LSST, and 0.809 for 10-year mock LSST observations. Performance appears to continually improve with the training set size. Models trained on fewer images perform better in absence of the lens galaxy light. However, with larger training data sets, information from the lens galaxy actually improves model performance, indicating that HOG captures much of the morphological complexity of the arc finding problem. We test our classifier on data from the Sloan Lens ACS Survey and find that small scale image features reduces the efficiency of our trained model. However, these preliminary tests indicate that some parameterizations of HOG can compensate for differences between observed mock data. One example best-case parameterization results in an AUC of 0.6 in the F814 filter image with other parameterization results equivalent to random performance.
In this paper we investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as specific concerns such as the inclusion of verifiably pornographic imag
es in datasets. Taking the ImageNet-ILSVRC-2012 dataset as an example, we perform a cross-sectional model-based quantitative census covering factors such as age, gender, NSFW content scoring, class-wise accuracy, human-cardinality-analysis, and the semanticity of the image class information in order to statistically investigate the extent and subtleties of ethical transgressions. We then use the census to help hand-curate a look-up-table of images in the ImageNet-ILSVRC-2012 dataset that fall into the categories of verifiably pornographic: shot in a non-consensual setting (up-skirt), beach voyeuristic, and exposed private parts. We survey the landscape of harm and threats both society broadly and individuals face due to uncritical and ill-considered dataset curation practices. We then propose possible courses of correction and critique the pros and cons of these. We have duly open-sourced all of the code and the census meta-datasets generated in this endeavor for the computer vision community to build on. By unveiling the severity of the threats, our hope is to motivate the constitution of mandatory Institutional Review Boards (IRB) for large scale dataset curation processes.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
