Emily Denton

Chitwan Saharia, William Chan, Saurabh Saxena et al. · deepmind

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation. Our key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset, without ever training on COCO, and human raters find Imagen samples to be on par with the COCO data itself in image-text alignment. To assess text-to-image models in greater depth, we introduce DrawBench, a comprehensive and challenging benchmark for text-to-image models. With DrawBench, we compare Imagen with recent methods including VQ-GAN+CLIP, Latent Diffusion Models, and DALL-E 2, and find that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment. See https://imagen.research.google/ for an overview of the results.

Emily Muller, Emily Gemmell, Ishmam Choudhury et al.

The interactions of individuals with city neighbourhoods is determined, in part, by the perceived quality of urban environments. Perceived neighbourhood quality is a core component of urban vitality, influencing social cohesion, sense of community, safety, activity and mental health of residents. Large-scale assessment of perceptions of neighbourhood quality was pioneered by the Place Pulse projects. Researchers demonstrated the efficacy of crowd-sourcing perception ratings of image pairs across 56 cities and training a model to predict perceptions from street-view images. Variation across cities may limit Place Pulse's usefulness for assessing within-city perceptions. In this paper, we set forth a protocol for city-specific dataset collection for the perception: 'On which street would you prefer to walk?'. This paper describes our methodology, based in London, including collection of images and ratings, web development, model training and mapping. Assessment of within-city perceptions of neighbourhoods can identify inequities, inform planning priorities, and identify temporal dynamics. Code available: https://emilymuller1991.github.io/urban-perceptions/.

Mark Diaz, Ian D. Kivlichan, Rachel Rosen et al.

Human annotated data plays a crucial role in machine learning (ML) research and development. However, the ethical considerations around the processes and decisions that go into dataset annotation have not received nearly enough attention. In this paper, we survey an array of literature that provides insights into ethical considerations around crowdsourced dataset annotation. We synthesize these insights, and lay out the challenges in this space along two layers: (1) who the annotator is, and how the annotators' lived experiences can impact their annotations, and (2) the relationship between the annotators and the crowdsourcing platforms, and what that relationship affords them. Finally, we introduce a novel framework, CrowdWorkSheets, for dataset developers to facilitate transparent documentation of key decisions points at various stages of the data annotation pipeline: task formulation, selection of annotators, platform and infrastructure choices, dataset analysis and evaluation, and dataset release and maintenance.

Rida Qadri, Piotr Mirowski, Aroussiak Gabriellan et al.

This paper proposes dialogue as a method for evaluating generative AI tools for culturally-situated creative practice, that recognizes the socially situated nature of art. Drawing on sociologist Howard Becker's concept of Art Worlds, this method expands the scope of traditional AI and creativity evaluations beyond benchmarks, user studies with crowd-workers, or focus groups conducted with artists. Our method involves two mutually informed dialogues: 1) 'dialogues with art worlds' placing artists in conversation with experts such as art historians, curators, and archivists, and 2)'dialogues with the machine,' facilitated through structured artist- and critic-led experimentation with state-of-the-art generative AI tools. We demonstrate the value of this method through a case study with artists and experts steeped in non-western art worlds, specifically the Persian Gulf. We trace how these dialogues help create culturally rich and situated forms of evaluation for representational possibilities of generative AI that mimic the reception of generative artwork in the broader art ecosystem. Putting artists in conversation with commentators also allow artists to shift their use of the tools to respond to their cultural and creative context. Our study can provide generative AI researchers an understanding of the complex dynamics of technology, human creativity and the socio-politics of art worlds, to build more inclusive machines for diverse art worlds.

Rida Qadri, Renee Shelby, Cynthia L. Bennett et al.

This paper presents a community-centered study of cultural limitations of text-to-image (T2I) models in the South Asian context. We theorize these failures using scholarship on dominant media regimes of representations and locate them within participants' reporting of their existing social marginalizations. We thus show how generative AI can reproduce an outsiders gaze for viewing South Asian cultures, shaped by global and regional power inequities. By centering communities as experts and soliciting their perspectives on T2I limitations, our study adds rich nuance into existing evaluative frameworks and deepens our understanding of the culturally-specific ways AI technologies can fail in non-Western and Global South settings. We distill lessons for responsible development of T2I models, recommending concrete pathways forward that can allow for recognition of structural inequalities.

Remi Denton, Mark Díaz, Ian Kivlichan et al.

Human annotations play a crucial role in machine learning (ML) research and development. However, the ethical considerations around the processes and decisions that go into building ML datasets has not received nearly enough attention. In this paper, we survey an array of literature that provides insights into ethical considerations around crowdsourced dataset annotation. We synthesize these insights, and lay out the challenges in this space along two layers: (1) who the annotator is, and how the annotators' lived experiences can impact their annotations, and (2) the relationship between the annotators and the crowdsourcing platforms and what that relationship affords them. Finally, we put forth a concrete set of recommendations and considerations for dataset developers at various stages of the ML data pipeline: task formulation, selection of annotators, platform and infrastructure choices, dataset analysis and evaluation, and dataset documentation and release.

Negar Rostamzadeh, Emily Denton, Linda Petrini

This paper offers a retrospective of what we learnt from organizing the workshop *Ethical Considerations in Creative applications of Computer Vision* at CVPR 2021 conference and, prior to that, a series of workshops on *Computer Vision for Fashion, Art and Design* at ECCV 2018, ICCV 2019, and CVPR 2020. We hope this reflection will bring artists and machine learning researchers into conversation around the ethical and social dimensions of creative applications of computer vision.

Bernard Koch, Emily Denton, Alex Hanna et al.

Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing concentration on fewer and fewer datasets within task communities, significant adoption of datasets from other tasks, and concentration across the field on datasets that have been introduced by researchers situated within a small number of elite institutions. Our results have implications for scientific evaluation, AI ethics, and equity/access within the field.

Inioluwa Deborah Raji, Emily M. Bender, Amandalynne Paullada et al.

There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational milestones on the path towards flexible and generalizable AI systems. State-of-the-art performance on these benchmarks is widely understood as indicative of progress towards these long-term goals. In this position paper, we explore the limits of such benchmarks in order to reveal the construct validity issues in their framing as the functionally "general" broad measures of progress they are set up to be.

Amandalynne Paullada, Inioluwa Deborah Raji, Emily M. Bender et al.

Datasets have played a foundational role in the advancement of machine learning research. They form the basis for the models we design and deploy, as well as our primary medium for benchmarking and evaluation. Furthermore, the ways in which we collect, construct and share these datasets inform the kinds of problems the field pursues and the methods explored in algorithm development. However, recent work from a breadth of perspectives has revealed the limitations of predominant practices in dataset collection and use. In this paper, we survey the many concerns raised about the way we collect and use data in machine learning and advocate that a more cautious and thorough understanding of data is necessary to address several of the practical and ethical issues of the field.

Ben Hutchinson, Andrew Smart, Alex Hanna et al.

Rising concern for the societal implications of artificial intelligence systems has inspired demands for greater transparency and accountability. However the datasets which empower machine learning are often used, shared and re-used with little visibility into the processes of deliberation which led to their creation. Which stakeholder groups had their perspectives included when the dataset was conceived? Which domain experts were consulted regarding how to model subgroups and other phenomena? How were questions of representational biases measured and addressed? Who labeled the data? In this paper, we introduce a rigorous framework for dataset development transparency which supports decision-making and accountability. The framework uses the cyclical, infrastructural and engineering nature of dataset development to draw on best practices from the software development lifecycle. Each stage of the data development lifecycle yields a set of documents that facilitate improved communication and decision-making, as well as drawing attention the value and necessity of careful data work. The proposed framework is intended to contribute to closing the accountability gap in artificial intelligence systems, by making visible the often overlooked work that goes into dataset creation.

Sara Hooker, Nyalleng Moorosi, Gregory Clark et al.

The popularity and widespread use of pruning and quantization is driven by the severe resource constraints of deploying deep neural networks to environments with strict latency, memory and energy requirements. These techniques achieve high levels of compression with negligible impact on top-line metrics (top-1 and top-5 accuracy). However, overall accuracy hides disproportionately high errors on a small subset of examples; we call this subset Compression Identified Exemplars (CIE). We further establish that for CIE examples, compression amplifies existing algorithmic bias. Pruning disproportionately impacts performance on underrepresented features, which often coincides with considerations of fairness. Given that CIE is a relatively small subset but a great contributor of error in the model, we propose its use as a human-in-the-loop auditing tool to surface a tractable subset of the dataset for further inspection or annotation by a domain expert. We provide qualitative and quantitative support that CIE surfaces the most challenging examples in the data distribution for human-in-the-loop auditing.

Ben Hutchinson, Vinodkumar Prabhakaran, Emily Denton et al.

Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained. In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.

Remi Denton, Ben Hutchinson, Margaret Mitchell et al.

Facial analysis models are increasingly used in applications that have serious impacts on people's lives, ranging from authentication to surveillance tracking. It is therefore critical to develop techniques that can reveal unintended biases in facial classifiers to help guide the ethical use of facial analysis technology. This work proposes a framework called \textit{image counterfactual sensitivity analysis}, which we explore as a proof-of-concept in analyzing a smiling attribute classifier trained on faces of celebrities. The framework utilizes counterfactuals to examine how a classifier's prediction changes if a face characteristic slightly changes. We leverage recent advances in generative adversarial networks to build a realistic generative model of face images that affords controlled manipulation of specific image characteristics. We then introduce a set of metrics that measure the effect of manipulating a specific property on the output of the trained classifier. Empirically, we find several different factors of variation that affect the predictions of the smiling classifier. This proof-of-concept demonstrates potential ways generative models can be leveraged for fine-grained analysis of bias and fairness.

Sainbayar Sukhbaatar, Emily Denton, Arthur Szlam et al.

In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can execute them. A high-level policy can then direct the lower one by generating a sequence of continuous sub-goal vectors. We evaluate our model using Mazebase and Mujoco environments, including the challenging AntGather task. Visualizations of the sub-goal embeddings reveal a logical decomposition of tasks within the environment. Quantitatively, our approach obtains compelling performance gains over non-hierarchical approaches.

Roberta Raileanu, Emily Denton, Arthur Szlam et al.

We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must infer the other players' hidden goals from their observed behavior in order to solve the tasks. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent's actions and update its belief of their hidden state in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players' hidden states, in both cooperative and adversarial settings.

Remi Denton, Rob Fergus

Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an unsupervised video generation model that learns a prior model of uncertainty in a given environment. Video frames are generated by drawing samples from this prior and combining them with a deterministic estimate of the future frame. The approach is simple and easily trained end-to-end on a variety of datasets. Sample generations are both varied and sharp, even many frames into the future, and compare favorably to those from existing approaches.

Remi Denton, Vighnesh Birodkar

We present a new model DrNET that learns disentangled image representations from video. Our approach leverages the temporal coherence of video and a novel adversarial loss to learn a representation that factorizes each frame into a stationary part and a temporally varying component. The disentangled representation can be used for a range of tasks. For example, applying a standard LSTM to the time-vary components enables prediction of future frames. We evaluate our approach on a range of synthetic and real videos, demonstrating the ability to coherently generate hundreds of steps into the future.

Remi Denton, Sam Gross, Rob Fergus

We introduce a simple semi-supervised learning approach for images based on in-painting using an adversarial loss. Images with random patches removed are presented to a generator whose task is to fill in the hole, based on the surrounding pixels. The in-painted images are then presented to a discriminator network that judges if they are real (unaltered training images) or not. This task acts as a regularizer for standard supervised training of the discriminator. Using our approach we are able to directly train large VGG-style networks in a semi-supervised fashion. We evaluate on STL-10 and PASCAL datasets, where our approach obtains performance comparable or superior to existing methods.

Emily Denton, Soumith Chintala, Arthur Szlam et al.

In this paper we introduce a generative parametric model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks within a Laplacian pyramid framework to generate images in a coarse-to-fine fashion. At each level of the pyramid, a separate generative convnet model is trained using the Generative Adversarial Nets (GAN) approach (Goodfellow et al.). Samples drawn from our model are of significantly higher quality than alternate approaches. In a quantitative assessment by human evaluators, our CIFAR10 samples were mistaken for real images around 40% of the time, compared to 10% for samples drawn from a GAN baseline model. We also show samples from models trained on the higher resolution images of the LSUN scene dataset.

Remi Denton, Wojciech Zaremba, Joan Bruna et al.

We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point operations, making their deployment on smartphones and Internet-scale clusters problematic. The computation is dominated by the convolution operations in the lower layers of the model. We exploit the linear structure present within the convolutional filters to derive approximations that significantly reduce the required computation. Using large state-of-the-art models, we demonstrate we demonstrate speedups of convolutional layers on both CPU and GPU by a factor of 2x, while keeping the accuracy within 1% of the original model.