{"total":156,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234,"area":null},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528,"area":null},{"id":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449,"area":null},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446,"area":null},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434,"area":null},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2202.06675","title":"Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2302.10893","title":"Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness","created":"2023-02-07","cited_by_count":151,"area":null},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133,"area":null},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113,"area":null},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108,"area":null},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2107.07919","title":"A Survey on Bias in Visual Datasets","created":"2021-07-16","cited_by_count":84,"area":null},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2104.02821","title":"Towards Measuring Fairness in AI: the Casual Conversations Dataset","created":"2021-04-06","cited_by_count":80,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2106.08320","title":"Self-Supervised Learning with Kernel Dependence Maximization","created":"2021-06-15","cited_by_count":77,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2106.04169","title":"On Improving Adversarial Transferability of Vision Transformers","created":"2021-06-08","cited_by_count":70,"area":null},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52,"area":null},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2301.02560","title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","created":"2023-01-05","cited_by_count":50,"area":null},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47,"area":null},{"id":"2105.02317","title":"A Step Toward More Inclusive People Annotations for Fairness","created":"2021-05-05","cited_by_count":46,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2207.07106","title":"Benchmarking Omni-Vision Representation through the Lens of Visual Realms","created":"2022-07-14","cited_by_count":38,"area":null},{"id":"2203.15395","title":"Quantifying Societal Bias Amplification in Image Captioning","created":"2022-03-29","cited_by_count":37,"area":null},{"id":"2206.07173","title":"Measuring Representational Harms in Image Captioning","created":"2022-06-14","cited_by_count":36,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2103.13023","title":"Can Vision Transformers Learn without Natural Images?","created":"2021-03-24","cited_by_count":32,"area":null},{"id":"2103.03399","title":"Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data","created":"2021-03-05","cited_by_count":31,"area":null},{"id":"2207.10888","title":"FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification","created":"2022-07-22","cited_by_count":30,"area":null},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2401.06310","title":"ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation","created":"2024-01-12","cited_by_count":27,"area":null},{"id":"2110.09253","title":"A Sociotechnical View of Algorithmic Fairness","created":"2021-09-27","cited_by_count":24,"area":null},{"id":"2202.07603","title":"Fairness Indicators for Systematic Assessments of Visual Feature Extractors","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2208.11695","title":"Bugs in the Data: How ImageNet Misrepresents Biodiversity","created":"2022-08-24","cited_by_count":24,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2207.10614","title":"A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2310.01755","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2206.09132","title":"Pre-training Vision Transformers with Formula-driven Supervised Learning","created":"2022-06-18","cited_by_count":21,"area":null},{"id":"2210.11924","title":"Men Also Do Laundry: Multi-Attribute Bias Amplification","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2405.01820","title":"Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2303.01112","title":"Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves","created":"2023-03-02","cited_by_count":20,"area":null},{"id":"2106.12887","title":"A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models","created":"2021-06-06","cited_by_count":19,"area":null},{"id":"2102.01393","title":"It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation","created":"2021-02-02","cited_by_count":18,"area":null},{"id":"2111.04424","title":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","created":"2021-10-18","cited_by_count":18,"area":null},{"id":"2102.03054","title":"Removing biased data to improve fairness and accuracy","created":"2021-02-05","cited_by_count":17,"area":null},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2304.03693","title":"Model-Agnostic Gender Debiased Image Captioning","created":"2023-04-07","cited_by_count":17,"area":null},{"id":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2104.06879","title":"Can Active Learning Preemptively Mitigate Fairness Issues?","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2203.04706","title":"Data Representativity for Machine Learning and AI Systems","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2412.01876","title":"Understanding Bias in Large-Scale Visual Datasets","created":"2024-12-02","cited_by_count":15,"area":null},{"id":"2104.09052","title":"Metadata Normalization","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2105.12754","title":"Computer Vision and Conflicting Values: Describing People with Automated Alt Text","created":"2021-05-26","cited_by_count":14,"area":null},{"id":"2304.10253","title":"Image retrieval outperforms diffusion models on data augmentation","created":"2023-04-20","cited_by_count":14,"area":"diffusion"},{"id":"2203.01854","title":"A study on the distribution of social biases in self-supervised learning visual models","created":"2022-03-03","cited_by_count":13,"area":null},{"id":"2204.05151","title":"Metaethical Perspectives on 'Benchmarking' AI Ethics","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2307.14710","title":"Pre-training Vision Transformers with Very Limited Synthesized Images","created":"2023-07-27","cited_by_count":12,"area":null},{"id":"2105.08997","title":"When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics","created":"2021-05-19","cited_by_count":11,"area":null},{"id":"2110.10389","title":"Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias","created":"2021-10-20","cited_by_count":11,"area":null},{"id":"2110.14336","title":"Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2202.10848","title":"Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animals","created":"2022-02-22","cited_by_count":11,"area":null},{"id":"2212.06641","title":"Simplicity Bias Leads to Amplified Performance Disparities","created":"2022-12-13","cited_by_count":11,"area":null},{"id":"2304.12622","title":"Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures","created":"2023-04-25","cited_by_count":11,"area":null},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11,"area":null},{"id":"2207.03444","title":"Fairness and Bias in Robot Learning","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2410.24100","title":"Benchmark Data Repositories for Better Benchmarking","created":"2024-10-31","cited_by_count":10,"area":null},{"id":"2205.15860","title":"A Reduction to Binary Approach for Debiasing Multiclass Datasets","created":"2022-05-31","cited_by_count":9,"area":null},{"id":"2309.02401","title":"Prototype-based Dataset Comparison","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2410.16432","title":"Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2309.17337","title":"Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2406.19614","title":"A Survey on Data Quality Dimensions and Tools for Machine Learning","created":"2024-06-28","cited_by_count":7,"area":null},{"id":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2207.08037","title":"Data Representativeness in Accessibility Datasets: A Meta-Analysis","created":"2022-07-16","cited_by_count":6,"area":null},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2209.08648","title":"Through a fair looking-glass: mitigating bias in image datasets","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2307.14119","title":"A semantics-driven methodology for high-quality image annotation","created":"2023-07-26","cited_by_count":6,"area":null},{"id":"2308.03348","title":"Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation","created":"2023-08-07","cited_by_count":6,"area":null},{"id":"2401.14322","title":"Generalized People Diversity: Learning a Human Perception-Aligned Diversity Representation for People Images","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2409.18055","title":"Visual Data Diagnosis and Debiasing with Concept Graphs","created":"2024-09-26","cited_by_count":6,"area":null},{"id":"2506.03117","title":"Targeted Forgetting of Image Subgroups in CLIP Models","created":"2025-06-03","cited_by_count":6,"area":"safety"},{"id":"2304.04874","title":"ImageCaptioner$^2$: Image Captioner for Image Captioning Bias Amplification Assessment","created":"2023-04-10","cited_by_count":5,"area":null},{"id":"2404.06717","title":"Racial/Ethnic Categories in AI and Algorithmic Fairness: Why They Matter and What They Represent","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2409.00252","title":"Building Better Datasets: Seven Recommendations for Responsible Design from Dataset Creators","created":"2024-08-30","cited_by_count":5,"area":null},{"id":"2507.08979","title":"PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection","created":"2025-07-11","cited_by_count":5,"area":"mllm"},{"id":"2303.04896","title":"Using Positive Matching Contrastive Loss with Facial Action Units to mitigate bias in Facial Expression Recognition","created":"2023-03-08","cited_by_count":4,"area":null},{"id":"2303.15219","title":"Knowing the Distance: Understanding the Gap Between Synthetic and Real Data For Face Parsing","created":"2023-03-27","cited_by_count":4,"area":null},{"id":"2401.15270","title":"SimFair: Physics-Guided Fairness-Aware Learning with Simulation Models","created":"2024-01-27","cited_by_count":4,"area":null},{"id":"2510.03721","title":"Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models","created":"2025-10-04","cited_by_count":4,"area":"mllm"},{"id":"2111.01785","title":"PatchGame: Learning to Signal Mid-level Patches in Referential Games","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2111.11056","title":"Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes","created":"2021-11-22","cited_by_count":3,"area":null}],"next_cursor":"100"}