{"total":75,"rows":[{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143,"area":null},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2310.04655","title":"VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models","created":"2023-10-07","cited_by_count":68,"area":null},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2305.13665","title":"Dual Focal Loss for Calibration","created":"2023-05-23","cited_by_count":33,"area":null},{"id":"2105.04019","title":"Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision","created":"2021-05-09","cited_by_count":31,"area":null},{"id":"2102.05289","title":"Bayesian Inference with Certifiable Adversarial Robustness","created":"2021-02-10","cited_by_count":26,"area":null},{"id":"2203.09630","title":"Monotonic Differentiable Sorting Networks","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2210.00788","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2106.06235","title":"Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks","created":"2021-06-11","cited_by_count":24,"area":null},{"id":"2206.15407","title":"Shifts 2.0: Extending The Dataset of Real Distributional Shifts","created":"2022-06-30","cited_by_count":24,"area":null},{"id":"2208.10159","title":"Prompt-Matched Semantic Segmentation","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2210.02074","title":"Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2309.06922","title":"Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning","created":"2023-09-13","cited_by_count":17,"area":null},{"id":"2201.07012","title":"Adversarial vulnerability of powerful near out-of-distribution detection","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2108.07848","title":"Multi-task learning for jersey number recognition in Ice Hockey","created":"2021-08-17","cited_by_count":15,"area":null},{"id":"2407.02894","title":"Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation","created":"2024-07-03","cited_by_count":14,"area":null},{"id":"2102.04150","title":"Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples","created":"2021-02-08","cited_by_count":13,"area":null},{"id":"2405.14700","title":"Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference","created":"2024-05-23","cited_by_count":12,"area":null},{"id":"2104.02107","title":"Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models","created":"2021-04-05","cited_by_count":10,"area":null},{"id":"2208.00777","title":"D3Former: Debiased Dual Distilled Transformer for Incremental Learning","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2302.06245","title":"Calibrating a Deep Neural Network with Its Predecessors","created":"2023-02-13","cited_by_count":9,"area":null},{"id":"2203.00734","title":"Knock, knock. Who's there? -- Identifying football player jersey numbers with synthetic data","created":"2022-03-01","cited_by_count":7,"area":null},{"id":"2305.01034","title":"Model-agnostic Measure of Generalization Difficulty","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2507.19360","title":"EA-ViT: Efficient Adaptation for Elastic Vision Transformer","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2111.14924","title":"Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design","created":"2021-11-29","cited_by_count":6,"area":null},{"id":"2306.01930","title":"Structural Similarities Between Language Models and Neural Response Measurements","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2411.01981","title":"Typicalness-Aware Learning for Failure Detection","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2110.15383","title":"New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis","created":"2021-10-28","cited_by_count":5,"area":null},{"id":"2211.05551","title":"Causal Counterfactuals for Improving the Robustness of Reinforcement Learning","created":"2022-11-02","cited_by_count":5,"area":null},{"id":"2305.10406","title":"Variational Classification","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2404.16828","title":"Made to Order: Discovering monotonic temporal changes via self-supervised video ordering","created":"2024-04-25","cited_by_count":5,"area":null},{"id":"2406.02322","title":"A Survey of Transformer Enabled Time Series Synthesis","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2406.15941","title":"Towards Exact Computation of Inductive Bias","created":"2024-06-22","cited_by_count":5,"area":null},{"id":"2408.11084","title":"Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2404.14265","title":"Deep Learning as Ricci Flow","created":"2024-04-22","cited_by_count":4,"area":null},{"id":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2301.01531","title":"MoBYv2AL: Self-supervised Active Learning for Image Classification","created":"2023-01-04","cited_by_count":3,"area":null},{"id":"2110.04954","title":"Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2201.04014","title":"Captcha Attack: Turning Captchas Against Humanity","created":"2022-01-11","cited_by_count":2,"area":null},{"id":"2206.05869","title":"On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2209.09844","title":"Frequency Dropout: Feature-Level Regularization via Randomized Filtering","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2210.11194","title":"Controller-Guided Partial Label Consistency Regularization with Unlabeled Data","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2505.11982","title":"FedHQ: Hybrid Runtime Quantization for Federated Learning","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2506.12041","title":"Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2601.21568","title":"Bridging Functional and Representational Similarity via Usable Information","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.02855","title":"When pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2102.08012","title":"Training Stacked Denoising Autoencoders for Representation Learning","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2103.01632","title":"Using CNNs to Identify the Origin of Finger Vein Image","created":"2021-03-02","cited_by_count":1,"area":null},{"id":"2111.07169","title":"Where to Look: A Unified Attention Model for Visual Recognition with Reinforcement Learning","created":"2021-11-13","cited_by_count":1,"area":null},{"id":"2207.12547","title":"The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2101.10862","title":"HANA: A HAndwritten NAme Database for Offline Handwritten Text Recognition","created":"2021-01-22","cited_by_count":0,"area":null},{"id":"2102.07354","title":"QuickBrowser: A Unified Model to Detect and Read Simple Object in Real-time","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2210.00503","title":"DARE: A large-scale handwritten date recognition system","created":"2022-10-02","cited_by_count":0,"area":null},{"id":"2210.10836","title":"Scene Text Recognition with Semantics","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2301.00504","title":"Spectral Bandwidth Recovery of Optical Coherence Tomography Images using Deep Learning","created":"2023-01-02","cited_by_count":0,"area":null},{"id":"2403.01339","title":"Uniform $\\mathcal{C}^k$ Approximation of $G$-Invariant and Antisymmetric Functions, Embedding Dimensions, and Polynomial Representations","created":"2024-03-02","cited_by_count":0,"area":null},{"id":"2404.08011","title":"An inclusive review on deep learning techniques and their scope in handwriting recognition","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2404.10370","title":"Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2408.10900","title":"Towards Efficient Formal Verification of Spiking Neural Network","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2408.14152","title":"Application of Disentanglement to Map Registration Problem","created":"2024-08-26","cited_by_count":0,"area":null},{"id":"2412.03058","title":"Revisiting Energy-Based Model for Out-of-Distribution Detection","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2503.20583","title":"Feature Statistics with Uncertainty Help Adversarial Robustness","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2505.11671","title":"Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.03229","title":"Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2509.09926","title":"LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2512.00676","title":"Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2603.08252","title":"FedPrism: Adaptive Personalized Federated Learning under Non-IID Data","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.23862","title":"Deep Convolutional Neural Networks for predicting highest priority functional group in organic molecules","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2606.09792","title":"End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.26099","title":"Lilith: Backdoor Generalization under Training-Inference Trigger Shift","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.09659","title":"Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}