{"total":21,"rows":[{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97,"area":null},{"id":"2303.08536","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","created":"2023-03-15","cited_by_count":42,"area":null},{"id":"2104.10824","title":"Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations","created":"2021-04-22","cited_by_count":38,"area":null},{"id":"2105.00999","title":"Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation","created":"2021-05-03","cited_by_count":34,"area":null},{"id":"2101.07422","title":"SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images","created":"2021-01-19","cited_by_count":33,"area":null},{"id":"2210.12333","title":"Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets","created":"2022-10-22","cited_by_count":15,"area":null},{"id":"2104.12898","title":"SGNet: A Super-class Guided Network for Image Classification and Object Detection","created":"2021-04-26","cited_by_count":13,"area":null},{"id":"2109.01926","title":"Audio-Visual Transformer Based Crowd Counting","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2105.05348","title":"Few-Shot Learning by Integrating Spatial and Frequency Representation","created":"2021-05-11","cited_by_count":11,"area":null},{"id":"2112.15555","title":"An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training","created":"2021-12-31","cited_by_count":10,"area":null},{"id":"2112.13165","title":"Semantic Clustering based Deduction Learning for Image Recognition and Classification","created":"2021-12-25","cited_by_count":8,"area":null},{"id":"2201.09396","title":"Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2409.10775","title":"Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks?","created":"2024-09-16","cited_by_count":5,"area":null},{"id":"2112.05861","title":"A Discriminative Channel Diversification Network for Image Classification","created":"2021-12-10","cited_by_count":4,"area":null},{"id":"2211.11950","title":"UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes","created":"2022-11-22","cited_by_count":3,"area":null},{"id":"2108.00610","title":"Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2021-08-02","cited_by_count":2,"area":null},{"id":"2112.09664","title":"Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network","created":"2021-12-17","cited_by_count":2,"area":null},{"id":"2210.14319","title":"Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2402.06936","title":"Latent Enhancing AutoEncoder for Occluded Image Classification","created":"2024-02-10","cited_by_count":1,"area":null},{"id":"2104.01730","title":"Training Deep Neural Networks via Branch-and-Bound","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2607.16274","title":"The JEPA Predictor: A Transferable Operator for Occluded Feature Completion","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}