{"list":"other","total":81,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1611.02648","title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","created":"2016-11-08","cited_by_count":220},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1603.08575","title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","created":"2016-03-28","cited_by_count":209},{"id":"1604.03628","title":"Joint Unsupervised Learning of Deep Representations and Image Clusters","created":"2016-04-13","cited_by_count":205},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2102.06191","title":"Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals","created":"2021-02-11","cited_by_count":190},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"1904.09146","title":"Salient Object Detection in the Deep Learning Era: An In-Depth Survey","created":"2019-04-19","cited_by_count":164},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"2205.07839","title":"Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization","created":"2022-05-16","cited_by_count":150},{"id":"1702.08720","title":"Learning Discrete Representations via Information Maximizing Self-Augmented Training","created":"2017-02-28","cited_by_count":149},{"id":"1806.01794","title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","created":"2018-06-05","cited_by_count":128},{"id":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"1901.07017","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","created":"2019-01-21","cited_by_count":117},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"1802.10353","title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","created":"2018-02-28","cited_by_count":100},{"id":"2105.13502","title":"Unsupervised Domain Adaptation of Object Detectors: A Survey","created":"2021-05-27","cited_by_count":93},{"id":"1906.06818","title":"Stacked Capsule Autoencoders","created":"2019-06-17","cited_by_count":82},{"id":"2203.08777","title":"Object discovery and representation networks","created":"2022-03-16","cited_by_count":80},{"id":"1905.13539","title":"Unsupervised Object Segmentation by Redrawing","created":"2019-05-27","cited_by_count":74},{"id":"1501.06170","title":"Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals","created":"2015-01-25","cited_by_count":69},{"id":"1606.06724","title":"Tagger: Deep Unsupervised Perceptual Grouping","created":"2016-06-21","cited_by_count":69},{"id":"2007.02662","title":"Toward unsupervised, multi-object discovery in large-scale image collections","created":"2020-07-06","cited_by_count":65},{"id":"1806.10206","title":"Deep Feature Factorization For Concept Discovery","created":"2018-06-26","cited_by_count":64},{"id":"1811.11155","title":"FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery","created":"2018-11-27","cited_by_count":58},{"id":"2010.12152","title":"Generative Neurosymbolic Machines","created":"2020-10-23","cited_by_count":57},{"id":"2203.12614","title":"Unsupervised Salient Object Detection with Spectral Cluster Voting","created":"2022-03-23","cited_by_count":56},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"id":"2002.08721","title":"A survey on Semi-, Self- and Unsupervised Learning for Image Classification","created":"2020-02-20","cited_by_count":55},{"id":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54},{"id":"2006.04988","title":"Object Segmentation Without Labels with Large-Scale Generative Models","created":"2020-06-08","cited_by_count":52},{"id":"1803.10910","title":"Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective","created":"2018-03-29","cited_by_count":50},{"id":"2006.12373","title":"Learning Physical Graph Representations from Visual Scenes","created":"2020-06-22","cited_by_count":50},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50},{"id":"1904.03148","title":"Unsupervised Image Matching and Object Discovery as Optimization","created":"2019-04-05","cited_by_count":42},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42},{"id":"1909.13055","title":"DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision","created":"2019-09-28","cited_by_count":38},{"id":"2004.12906","title":"Towards causal generative scene models via competition of experts","created":"2020-04-27","cited_by_count":37},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37},{"id":"2106.03630","title":"Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations","created":"2021-06-07","cited_by_count":36},{"id":"2104.14553","title":"MarioNette: Self-Supervised Sprite Learning","created":"2021-04-29","cited_by_count":35},{"id":"2110.14711","title":"A Survey of Self-Supervised and Few-Shot Object Detection","created":"2021-10-27","cited_by_count":35},{"id":"1905.11369","title":"Object Discovery with a Copy-Pasting GAN","created":"2019-05-27","cited_by_count":29},{"id":"2006.11132","title":"Deep Transformation-Invariant Clustering","created":"2020-06-19","cited_by_count":26},{"id":"2110.15497","title":"Unsupervised Foreground Extraction via Deep Region Competition","created":"2021-10-29","cited_by_count":26},{"id":"2004.05495","title":"Learning to Manipulate Individual Objects in an Image","created":"2020-04-11","cited_by_count":22},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22},{"id":"1902.09968","title":"Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features","created":"2019-02-26","cited_by_count":19},{"id":"2210.12148","title":"Unsupervised Multi-object Segmentation by Predicting Probable Motion Patterns","created":"2022-10-21","cited_by_count":19},{"id":"2310.12904","title":"Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey","created":"2023-10-19","cited_by_count":16},{"id":"1707.06397","title":"Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming","created":"2017-07-20","cited_by_count":15},{"id":"2110.15904","title":"Learning Co-segmentation by Segment Swapping for Retrieval and Discovery","created":"2021-10-29","cited_by_count":15},{"id":"1612.03236","title":"Co-localization with Category-Consistent Features and Geodesic Distance Propagation","created":"2016-12-10","cited_by_count":14},{"id":"2204.10926","title":"SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation","created":"2022-04-22","cited_by_count":13},{"id":"1511.06362","title":"Efficient inference in occlusion-aware generative models of images","created":"2015-11-19","cited_by_count":11},{"id":"1603.04619","title":"Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution","created":"2016-03-15","cited_by_count":5},{"id":"1902.02693","title":"StampNet: unsupervised multi-class object discovery","created":"2019-02-07","cited_by_count":4},{"id":"2106.01722","title":"GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture","created":"2021-06-03","cited_by_count":3},{"id":"1408.5418","title":"Hierarchical Saliency Detection on Extended CSSD","created":"2014-08-11","cited_by_count":2},{"id":"2104.14735","title":"DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing","created":"2021-04-30","cited_by_count":2},{"id":"2106.08599","title":"PatchNet: Unsupervised Object Discovery based on Patch Embedding","created":"2021-06-16","cited_by_count":2},{"id":"2107.02453","title":"Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering","created":"2021-07-06","cited_by_count":2}],"next_cursor":null}