{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"1710.00935","title":"Interpretable Convolutional Neural Networks","created":"2017-10-02","cited_by_count":162},{"id":"2107.10912","title":"Explainable artificial intelligence (XAI) in deep learning-based medical image analysis","created":"2021-07-22","cited_by_count":147},{"id":"1511.06078","title":"Learning Deep Structure-Preserving Image-Text Embeddings","created":"2015-11-19","cited_by_count":139},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132},{"id":"2008.01392","title":"Learning Visual Representations with Caption Annotations","created":"2020-08-04","cited_by_count":123},{"id":"1702.00758","title":"HashNet: Deep Learning to Hash by Continuation","created":"2017-02-02","cited_by_count":122},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"2011.14340","title":"ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery","created":"2020-11-29","cited_by_count":89},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79},{"id":"1908.00347","title":"Central Similarity Quantization for Efficient Image and Video Retrieval","created":"2019-08-01","cited_by_count":77},{"id":"2005.10411","title":"Interpretable and Accurate Fine-grained Recognition via Region Grouping","created":"2020-05-21","cited_by_count":75},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71},{"id":"1809.05934","title":"Maximum-Entropy Fine-Grained Classification","created":"2018-09-16","cited_by_count":65},{"id":"2002.04264","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","created":"2020-02-11","cited_by_count":64},{"id":"1806.05372","title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","created":"2018-06-14","cited_by_count":58},{"id":"1704.01740","title":"Object-Part Attention Model for Fine-grained Image Classification","created":"2017-04-06","cited_by_count":54},{"id":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49},{"id":"2003.03369","title":"A Survey on Deep Hashing Methods","created":"2020-03-04","cited_by_count":47},{"id":"1504.03410","title":"Simultaneous Feature Learning and Hash Coding with Deep Neural Networks","created":"2015-04-14","cited_by_count":44},{"id":"2109.14449","title":"One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective","created":"2021-09-29","cited_by_count":43},{"id":"2107.02341","title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","created":"2021-07-06","cited_by_count":40},{"id":"2201.13182","title":"Learning Super-Features for Image Retrieval","created":"2022-01-31","cited_by_count":35},{"id":"2203.06345","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","created":"2022-03-12","cited_by_count":35},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32},{"id":"2101.06635","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","created":"2021-01-17","cited_by_count":31},{"id":"1612.03900","title":"Deep Supervised Hashing with Triplet Labels","created":"2016-12-12","cited_by_count":27},{"id":"1912.06842","title":"Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes","created":"2019-12-14","cited_by_count":24},{"id":"2112.02290","title":"Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations","created":"2021-12-04","cited_by_count":24},{"id":"2203.15987","title":"Fine-Grained Object Classification via Self-Supervised Pose Alignment","created":"2022-03-30","cited_by_count":22},{"id":"2012.12334","title":"Deep Unsupervised Image Hashing by Maximizing Bit Entropy","created":"2020-12-22","cited_by_count":20},{"id":"2203.08543","title":"Integrating Language Guidance into Vision-based Deep Metric Learning","created":"2022-03-16","cited_by_count":19},{"id":"2008.01369","title":"ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval","created":"2020-08-04","cited_by_count":16},{"id":"1606.05032","title":"Zero-Shot Hashing via Transferring Supervised Knowledge","created":"2016-06-16","cited_by_count":15},{"id":"1807.01459","title":"Deep Saliency Hashing","created":"2018-07-04","cited_by_count":11},{"id":"2209.13833","title":"SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval","created":"2022-09-28","cited_by_count":11},{"id":"2211.12760","title":"InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images","created":"2022-11-23","cited_by_count":5},{"id":"2109.05206","title":"PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval","created":"2021-09-11","cited_by_count":3}],"next_cursor":null}