{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"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":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1604.05144","title":"ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation","created":"2016-04-18","cited_by_count":331},{"id":"1506.02106","title":"What's the Point: Semantic Segmentation with Point Supervision","created":"2015-06-06","cited_by_count":298},{"id":"2203.08414","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","created":"2022-03-16","cited_by_count":241},{"id":"1503.01640","title":"BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation","created":"2015-03-05","cited_by_count":238},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230},{"id":"1603.07485","title":"Simple Does It: Weakly Supervised Instance and Semantic Segmentation","created":"2016-03-24","cited_by_count":227},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"2102.06191","title":"Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals","created":"2021-02-11","cited_by_count":190},{"id":"1502.02734","title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","created":"2015-02-09","cited_by_count":189},{"id":"1703.04044","title":"Colorization as a Proxy Task for Visual Understanding","created":"2017-03-11","cited_by_count":175},{"id":"1802.07934","title":"Adversarial Learning for Semi-Supervised Semantic Segmentation","created":"2018-02-22","cited_by_count":173},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"2001.06902","title":"MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning","created":"2020-01-19","cited_by_count":157},{"id":"1708.01566","title":"Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes","created":"2017-08-04","cited_by_count":122},{"id":"1803.09569","title":"On Regularized Losses for Weakly-supervised CNN Segmentation","created":"2018-03-26","cited_by_count":121},{"id":"1804.01346","title":"Normalized Cut Loss for Weakly-supervised CNN Segmentation","created":"2018-04-04","cited_by_count":112},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"1704.05310","title":"Unsupervised Learning by Predicting Noise","created":"2017-04-18","cited_by_count":98},{"id":"1910.06962","title":"SegSort: Segmentation by Discriminative Sorting of Segments","created":"2019-10-15","cited_by_count":96},{"id":"1805.00385","title":"Boosting Self-Supervised Learning via Knowledge Transfer","created":"2018-05-01","cited_by_count":92},{"id":"1912.03330","title":"ClusterFit: Improving Generalization of Visual Representations","created":"2019-12-06","cited_by_count":82},{"id":"1901.04596","title":"AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data","created":"2019-01-14","cited_by_count":77},{"id":"2007.02662","title":"Toward unsupervised, multi-object discovery in large-scale image collections","created":"2020-07-06","cited_by_count":65},{"id":"2012.03044","title":"Self-Supervised Visual Representation Learning from Hierarchical Grouping","created":"2020-12-05","cited_by_count":63},{"id":"2001.01306","title":"Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis","created":"2020-01-05","cited_by_count":61},{"id":"2007.08247","title":"Autoregressive Unsupervised Image Segmentation","created":"2020-07-16","cited_by_count":60},{"id":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54},{"id":"2106.05967","title":"Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations","created":"2021-06-10","cited_by_count":48},{"id":"1511.06811","title":"Learning visual groups from co-occurrences in space and time","created":"2015-11-21","cited_by_count":42},{"id":"1506.04924","title":"Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation","created":"2015-06-16","cited_by_count":23},{"id":"1605.06885","title":"Bridging Category-level and Instance-level Semantic Image Segmentation","created":"2016-05-23","cited_by_count":21},{"id":"1807.05636","title":"Cross Pixel Optical Flow Similarity for Self-Supervised Learning","created":"2018-07-15","cited_by_count":21},{"id":"1903.11412","title":"Self-Supervised Learning via Conditional Motion Propagation","created":"2019-03-27","cited_by_count":20},{"id":"1505.02146","title":"DeepBox: Learning Objectness with Convolutional Networks","created":"2015-05-08","cited_by_count":14}],"next_cursor":null}