{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"1807.07356","title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","created":"2018-07-19","cited_by_count":280},{"id":"2211.13445","title":"Delving into Out-of-Distribution Detection with Vision-Language Representations","created":"2022-11-24","cited_by_count":216},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"1904.09658","title":"Probabilistic Face Embeddings","created":"2019-04-21","cited_by_count":173},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116},{"id":"2007.02915","title":"Are Labels Always Necessary for Classifier Accuracy Evaluation?","created":"2020-07-06","cited_by_count":104},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89},{"id":"1906.04402","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","created":"2019-06-11","cited_by_count":83},{"id":"1805.11327","title":"Lightweight Probabilistic Deep Networks","created":"2018-05-29","cited_by_count":77},{"id":"2106.05961","title":"What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?","created":"2021-06-10","cited_by_count":63},{"id":"1607.06215","title":"A Comprehensive Survey on Cross-modal Retrieval","created":"2016-07-21","cited_by_count":62},{"id":"2111.12940","title":"Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation","created":"2021-11-25","cited_by_count":57},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57},{"id":"2007.03511","title":"Estimating Generalization under Distribution Shifts via Domain-Invariant Representations","created":"2020-07-06","cited_by_count":56},{"id":"2107.00643","title":"Mandoline: Model Evaluation under Distribution Shift","created":"2021-07-01","cited_by_count":55},{"id":"2301.06309","title":"UATVR: Uncertainty-Adaptive Text-Video Retrieval","created":"2023-01-16","cited_by_count":55},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"1912.01001","title":"View-Invariant Probabilistic Embedding for Human Pose","created":"2019-12-02","cited_by_count":47},{"id":"2208.07591","title":"Uncertainty-guided Source-free Domain Adaptation","created":"2022-08-16","cited_by_count":46},{"id":"2108.01634","title":"Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation","created":"2021-08-03","cited_by_count":40},{"id":"1912.11316","title":"TRADI: Tracking deep neural network weight distributions for uncertainty estimation","created":"2019-12-24","cited_by_count":39},{"id":"1909.09389","title":"Sampling Bias in Deep Active Classification: An Empirical Study","created":"2019-09-20","cited_by_count":36},{"id":"2103.05271","title":"Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation","created":"2021-03-09","cited_by_count":35},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29},{"id":"2302.02865","title":"Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs","created":"2023-02-06","cited_by_count":29},{"id":"1702.08540","title":"Active Learning Using Uncertainty Information","created":"2017-02-27","cited_by_count":28},{"id":"2208.02005","title":"Gradient-based Uncertainty for Monocular Depth Estimation","created":"2022-08-03","cited_by_count":26},{"id":"2101.09113","title":"Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions","created":"2021-01-22","cited_by_count":23},{"id":"2207.06873","title":"BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks","created":"2022-07-14","cited_by_count":23},{"id":"2110.15784","title":"Convergence of Uncertainty Sampling for Active Learning","created":"2021-10-29","cited_by_count":19},{"id":"2107.09892","title":"Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data","created":"2021-07-21","cited_by_count":18},{"id":"2102.12959","title":"Bayesian OOD detection with aleatoric uncertainty and outlier exposure","created":"2021-02-24","cited_by_count":16},{"id":"2106.15542","title":"Uncertainty-Guided Progressive GANs for Medical Image Translation","created":"2021-06-29","cited_by_count":16},{"id":"2110.12467","title":"Robustness via Uncertainty-aware Cycle Consistency","created":"2021-10-24","cited_by_count":16},{"id":"2110.03343","title":"Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement","created":"2021-10-07","cited_by_count":15},{"id":"2110.11182","title":"SLURP: Side Learning Uncertainty for Regression Problems","created":"2021-10-21","cited_by_count":12},{"id":"2105.13688","title":"Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving","created":"2021-05-28","cited_by_count":8},{"id":"2305.17520","title":"USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution","created":"2023-05-27","cited_by_count":4}],"next_cursor":null}