{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"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":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"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":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1511.04599","title":"DeepFool: a simple and accurate method to fool deep neural networks","created":"2015-11-14","cited_by_count":1318},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"1703.08603","title":"Adversarial Examples for Semantic Segmentation and Object Detection","created":"2017-03-24","cited_by_count":275},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"1803.11285","title":"Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking","created":"2018-03-29","cited_by_count":191},{"id":"2006.07589","title":"Adversarial Self-Supervised Contrastive Learning","created":"2020-06-13","cited_by_count":139},{"id":"2206.10550","title":"(Certified!!) Adversarial Robustness for Free!","created":"2022-06-21","cited_by_count":132},{"id":"2212.07016","title":"Understanding Zero-Shot Adversarial Robustness for Large-Scale Models","created":"2022-12-14","cited_by_count":117},{"id":"2408.08872","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","created":"2024-08-16","cited_by_count":116},{"id":"2006.12792","title":"RayS: A Ray Searching Method for Hard-label Adversarial Attack","created":"2020-06-23","cited_by_count":96},{"id":"2112.09581","title":"Watermarking Images in Self-Supervised Latent Spaces","created":"2021-12-17","cited_by_count":94},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88},{"id":"2309.14700","title":"Structure Invariant Transformation for better Adversarial Transferability","created":"2023-09-26","cited_by_count":62},{"id":"2011.12807","title":"SurFree: a fast surrogate-free black-box attack","created":"2020-11-25","cited_by_count":60},{"id":"2102.12827","title":"Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints","created":"2021-02-25","cited_by_count":50},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35},{"id":"2403.17301","title":"Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving","created":"2024-03-26","cited_by_count":32},{"id":"2010.03072","title":"Adversarial Patch Attacks on Monocular Depth Estimation Networks","created":"2020-10-06","cited_by_count":29},{"id":"1905.04016","title":"Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables","created":"2019-05-10","cited_by_count":26},{"id":"1908.09163","title":"Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Tower","created":"2019-08-24","cited_by_count":26},{"id":"2308.03163","title":"CGBA: Curvature-aware Geometric Black-box Attack","created":"2023-08-06","cited_by_count":21},{"id":"2308.14597","title":"Adversarial Attacks on Foundational Vision Models","created":"2023-08-28","cited_by_count":13},{"id":"2010.07258","title":"Self-Supervised Ranking for Representation Learning","created":"2020-10-14","cited_by_count":10},{"id":"2210.10620","title":"Active Image Indexing","created":"2022-10-05","cited_by_count":8},{"id":"2308.02525","title":"Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?","created":"2023-07-31","cited_by_count":5},{"id":"2406.02361","title":"Using Self-supervised Learning Can Improve Model Fairness","created":"2024-06-04","cited_by_count":5},{"id":"2206.06761","title":"Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO","created":"2022-06-14","cited_by_count":4},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3}],"next_cursor":null}