{"total":119,"rows":[{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527,"area":null},{"id":"2101.04061","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","created":"2021-01-11","cited_by_count":349,"area":null},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73,"area":null},{"id":"2104.14335","title":"ELF-VC: Efficient Learned Flexible-Rate Video Coding","created":"2021-04-29","cited_by_count":69,"area":null},{"id":"2109.05472","title":"Compute and Energy Consumption Trends in Deep Learning Inference","created":"2021-09-12","cited_by_count":61,"area":null},{"id":"2211.04533","title":"Harmonizing the object recognition strategies of deep neural networks with humans","created":"2022-11-08","cited_by_count":59,"area":null},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58,"area":null},{"id":"2106.14851","title":"Data Poisoning Won't Save You From Facial Recognition","created":"2021-06-28","cited_by_count":45,"area":"safety"},{"id":"2101.00590","title":"RegNet: Self-Regulated Network for Image Classification","created":"2021-01-03","cited_by_count":44,"area":null},{"id":"2203.04600","title":"Domain Generalization using Pretrained Models without Fine-tuning","created":"2022-03-09","cited_by_count":29,"area":null},{"id":"2101.00440","title":"Refining activation downsampling with SoftPool","created":"2021-01-02","cited_by_count":26,"area":null},{"id":"2107.08621","title":"Face.evoLVe: A High-Performance Face Recognition Library","created":"2021-07-19","cited_by_count":26,"area":null},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26,"area":null},{"id":"2105.01563","title":"Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition","created":"2021-05-04","cited_by_count":22,"area":null},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21,"area":null},{"id":"2307.14039","title":"Controllable Guide-Space for Generalizable Face Forgery Detection","created":"2023-07-26","cited_by_count":21,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2306.03779","title":"Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex","created":"2023-06-06","cited_by_count":18,"area":null},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16,"area":null},{"id":"2110.04960","title":"Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systems","created":"2021-10-11","cited_by_count":15,"area":null},{"id":"2107.04228","title":"Activated Gradients for Deep Neural Networks","created":"2021-07-09","cited_by_count":14,"area":null},{"id":"2409.09649","title":"SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks","created":"2024-09-15","cited_by_count":14,"area":"ssm"},{"id":"2110.11852","title":"Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation","created":"2021-10-22","cited_by_count":13,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2405.01725","title":"Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey","created":"2024-05-02","cited_by_count":10,"area":null},{"id":"2105.10190","title":"AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks","created":"2021-05-21","cited_by_count":9,"area":null},{"id":"2412.07022","title":"Dense Cross-Connected Ensemble Convolutional Neural Networks for Enhanced Model Robustness","created":"2024-12-09","cited_by_count":9,"area":null},{"id":"2110.15764","title":"{\\epsilon}-weakened Robustness of Deep Neural Networks","created":"2021-10-29","cited_by_count":8,"area":null},{"id":"2411.16782","title":"Scaling Laws for Black box Adversarial Attacks","created":"2024-11-25","cited_by_count":8,"area":null},{"id":"2103.08640","title":"UPANets: Learning from the Universal Pixel Attention Networks","created":"2021-03-15","cited_by_count":7,"area":null},{"id":"2105.00113","title":"IPatch: A Remote Adversarial Patch","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2110.01939","title":"Double Encoder-Decoder Networks for Gastrointestinal Polyp Segmentation","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2111.13841","title":"Adaptive Perturbation for Adversarial Attack","created":"2021-11-27","cited_by_count":7,"area":null},{"id":"2205.06265","title":"ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training","created":"2022-05-12","cited_by_count":7,"area":null},{"id":"2306.03229","title":"Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2103.17086","title":"Deep adaptive fuzzy clustering for evolutionary unsupervised representation learning","created":"2021-03-31","cited_by_count":6,"area":null},{"id":"2109.00707","title":"Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2603.15619","title":"Mixture-of-Depths Attention","created":"2026-03-16","cited_by_count":6,"area":null},{"id":"2102.10557","title":"Contrastive Self-supervised Neural Architecture Search","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2109.08791","title":"Small Lesion Segmentation in Brain MRIs with Subpixel Embedding","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2110.10965","title":"2020 CATARACTS Semantic Segmentation Challenge","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2304.12492","title":"Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2407.01316","title":"Evaluating Model Performance Under Worst-case Subpopulations","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2111.11397","title":"Lebanon Solar Rooftop Potential Assessment using Buildings Segmentation from Aerial Images","created":"2021-11-22","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2301.09318","title":"Toward Foundation Models for Earth Monitoring: Generalizable Deep Learning Models for Natural Hazard Segmentation","created":"2023-01-23","cited_by_count":4,"area":null},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2309.17334","title":"Multi-Depth Branch Network for Efficient Image Super-Resolution","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2401.17972","title":"MelNet: A Real-Time Deep Learning Algorithm for Object Detection","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2403.12562","title":"PePR: Performance Per Resource Unit as a Metric to Promote Small-Scale Deep Learning in Medical Image Analysis","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2510.02302","title":"Knowledge Distillation Detection for Open-weights Models","created":"2025-10-02","cited_by_count":4,"area":"distill"},{"id":"2102.11506","title":"Comparative evaluation of CNN architectures for Image Caption Generation","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2210.15943","title":"Grafting Vision Transformers","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2304.02867","title":"Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2306.11977","title":"Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2503.12453","title":"Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2505.14572","title":"Automated Fetal Biometry Assessment with Deep Ensembles using Sparse-Sampling of 2D Intrapartum Ultrasound Images","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2101.06848","title":"Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2111.06812","title":"Sci-Net: Scale Invariant Model for Buildings Segmentation from Aerial Imagery","created":"2021-11-12","cited_by_count":2,"area":null},{"id":"2112.10324","title":"Product Re-identification System in Fully Automated Defect Detection","created":"2021-12-20","cited_by_count":2,"area":null},{"id":"2203.08898","title":"Neural network processing of holographic images","created":"2022-03-16","cited_by_count":2,"area":null},{"id":"2203.10435","title":"Vision Transformer with Convolutions Architecture Search","created":"2022-03-20","cited_by_count":2,"area":null},{"id":"2301.10750","title":"Out of Distribution Performance of State of Art Vision Model","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2308.03821","title":"Distributionally Robust Classification on a Data Budget","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2505.12644","title":"Use as Many Surrogates as You Want: Selective Ensemble Attack to Unleash Transferability without Sacrificing Resource Efficiency","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2102.05368","title":"RoBIC: A benchmark suite for assessing classifiers robustness","created":"2021-02-10","cited_by_count":1,"area":null},{"id":"2105.04354","title":"AFINet: Attentive Feature Integration Networks for Image Classification","created":"2021-05-10","cited_by_count":1,"area":null},{"id":"2105.11863","title":"CoRSAI: A System for Robust Interpretation of CT Scans of COVID-19 Patients Using Deep Learning","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2106.06159","title":"Learning the Precise Feature for Cluster Assignment","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2110.13036","title":"Dual Skip Connections Minimize the False Positive Rate of Lung Nodule Detection in CT images","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2111.05789","title":"Evaluation of Deep Learning Topcoders Method for Neuron Individualization in Histological Macaque Brain Section","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2112.06121","title":"Magnifying Networks for Images with Billions of Pixels","created":"2021-12-12","cited_by_count":1,"area":null},{"id":"2208.14508","title":"Swin-transformer-yolov5 For Real-time Wine Grape Bunch Detection","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2209.01848","title":"A Principled Evaluation Protocol for Comparative Investigation of the Effectiveness of DNN Classification Models on Similar-but-non-identical Datasets","created":"2022-09-05","cited_by_count":1,"area":null},{"id":"2301.06635","title":"Data-aware customization of activation functions reduces neural network error","created":"2023-01-16","cited_by_count":1,"area":null},{"id":"2303.07679","title":"Feature representations useful for predicting image memorability","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2304.12448","title":"Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning","created":"2023-04-24","cited_by_count":1,"area":null},{"id":"2309.08139","title":"Multi-Scale Estimation for Omni-Directional Saliency Maps Using Learnable Equator Bias","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2401.13998","title":"WAL-Net: Weakly supervised auxiliary task learning network for carotid plaques classification","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2510.27263","title":"ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2102.01460","title":"Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks","created":"2021-02-02","cited_by_count":0,"area":null},{"id":"2105.09683","title":"DPN-SENet:A self-attention mechanism neural network for detection and diagnosis of COVID-19 from chest x-ray images","created":"2021-05-20","cited_by_count":0,"area":null},{"id":"2107.08770","title":"Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2112.15386","title":"Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning","created":"2021-12-31","cited_by_count":0,"area":null},{"id":"2201.04769","title":"MAg: a simple learning-based patient-level aggregation method for detecting microsatellite instability from whole-slide images","created":"2022-01-13","cited_by_count":0,"area":null},{"id":"2201.09144","title":"Background Invariant Classification on Infrared Imagery by Data Efficient Training and Reducing Bias in CNNs","created":"2022-01-22","cited_by_count":0,"area":null},{"id":"2201.11996","title":"Deep Networks for Image and Video Super-Resolution","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2201.11998","title":"Image Superresolution using Scale-Recurrent Dense Network","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2202.03540","title":"SliTraNet: Automatic Detection of Slide Transitions in Lecture Videos using Convolutional Neural Networks","created":"2022-02-07","cited_by_count":0,"area":null},{"id":"2202.04650","title":"Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network","created":"2022-02-09","cited_by_count":0,"area":null}],"next_cursor":"100"}