{"total":77,"rows":[{"id":"2301.10343","title":"ClimaX: A foundation model for weather and climate","created":"2023-01-24","cited_by_count":337,"area":null},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2208.08914","title":"Prompt Vision Transformer for Domain Generalization","created":"2022-08-18","cited_by_count":52,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2206.05514","title":"Toward Real-world Single Image Deraining: A New Benchmark and Beyond","created":"2022-06-11","cited_by_count":40,"area":null},{"id":"2206.03452","title":"Can CNNs Be More Robust Than Transformers?","created":"2022-06-07","cited_by_count":38,"area":null},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2205.01643","title":"MTTrans: Cross-Domain Object Detection with Mean-Teacher Transformer","created":"2022-05-03","cited_by_count":35,"area":null},{"id":"2207.12392","title":"Self-Distilled Vision Transformer for Domain Generalization","created":"2022-07-25","cited_by_count":35,"area":null},{"id":"2308.03322","title":"Part-Aware Transformer for Generalizable Person Re-identification","created":"2023-08-07","cited_by_count":35,"area":null},{"id":"2207.11347","title":"An Impartial Take to the CNN vs Transformer Robustness Contest","created":"2022-07-22","cited_by_count":34,"area":null},{"id":"2209.07027","title":"Out-of-Distribution Representation Learning for Time Series Classification","created":"2022-09-15","cited_by_count":31,"area":null},{"id":"2205.11083","title":"Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation","created":"2022-05-23","cited_by_count":24,"area":null},{"id":"2308.02282","title":"DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization","created":"2023-08-04","cited_by_count":24,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2309.10808","title":"AI Foundation Models for Weather and Climate: Applications, Design, and Implementation","created":"2023-09-19","cited_by_count":21,"area":null},{"id":"2407.15085","title":"Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization","created":"2024-07-21","cited_by_count":14,"area":null},{"id":"2208.12967","title":"Anti-Retroactive Interference for Lifelong Learning","created":"2022-08-27","cited_by_count":13,"area":null},{"id":"2402.08228","title":"Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective","created":"2024-02-13","cited_by_count":13,"area":null},{"id":"2405.15018","title":"What Variables Affect Out-of-Distribution Generalization in Pretrained Models?","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2209.14974","title":"Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification","created":"2022-09-26","cited_by_count":12,"area":null},{"id":"2402.09530","title":"Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2404.04452","title":"Vision transformers in domain adaptation and domain generalization: a study of robustness","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2201.11620","title":"Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study","created":"2022-01-27","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":"2303.15698","title":"TFS-ViT: Token-Level Feature Stylization for Domain Generalization","created":"2023-03-28","cited_by_count":10,"area":null},{"id":"2402.17562","title":"An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2412.13573","title":"Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes","created":"2024-12-18","cited_by_count":10,"area":null},{"id":"2404.15786","title":"Rethinking model prototyping through the MedMNIST+ dataset collection","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2211.16632","title":"Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomics","created":"2022-11-29","cited_by_count":8,"area":null},{"id":"2307.00648","title":"Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization","created":"2023-07-02","cited_by_count":8,"area":null},{"id":"2401.09716","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2305.09160","title":"SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification","created":"2023-05-16","cited_by_count":6,"area":null},{"id":"2408.14131","title":"GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2307.08187","title":"An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration","created":"2023-07-17","cited_by_count":5,"area":null},{"id":"2502.18273","title":"Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2301.03169","title":"A Study on the Generality of Neural Network Structures for Monocular Depth Estimation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2401.13965","title":"Improving Pseudo-labelling and Enhancing Robustness for Semi-Supervised Domain Generalization","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2403.04523","title":"T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2404.18933","title":"Learning Low-Rank Feature for Thorax Disease Classification","created":"2024-02-14","cited_by_count":4,"area":null},{"id":"2406.09647","title":"OpenAnimalTracks: A Dataset for Animal Track Recognition","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2506.02843","title":"Random Registers for Cross-Domain Few-Shot Learning","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2302.10718","title":"Effects of Architectures on Continual Semantic Segmentation","created":"2023-02-21","cited_by_count":3,"area":null},{"id":"2311.12856","title":"Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer","created":"2023-10-24","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":"2504.19574","title":"DG-DETR: Toward Domain Generalized Detection Transformer","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2206.05912","title":"INDIGO: Intrinsic Multimodality for Domain Generalization","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2212.02739","title":"Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation","created":"2022-12-06","cited_by_count":2,"area":null},{"id":"2310.04412","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2412.19124","title":"Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impact","created":"2024-12-26","cited_by_count":2,"area":null},{"id":"2501.10197","title":"CSHNet: A Novel Information Asymmetric Image Translation Method","created":"2025-01-17","cited_by_count":2,"area":null},{"id":"2601.07795","title":"Vision-Language Model for Accurate Crater Detection","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2210.12599","title":"Transformers For Recognition In Overhead Imagery: A Reality Check","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2311.13623","title":"Density Distribution-based Learning Framework for Addressing Online Continual Learning Challenges","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2402.14976","title":"Unsupervised Domain Adaptation within Deep Foundation Latent Spaces","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2407.07763","title":"S&D Messenger: Exchanging Semantic and Domain Knowledge for Generic Semi-Supervised Medical Image Segmentation","created":"2024-07-10","cited_by_count":1,"area":null},{"id":"2506.20575","title":"Exploring Graph-Transformer Out-of-Distribution Generalization Abilities","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2507.10239","title":"Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2603.26721","title":"Stress Classification from ECG Signals Using Vision Transformer","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2112.13989","title":"Associative Adversarial Learning Based on Selective Attack","created":"2021-12-28","cited_by_count":0,"area":null},{"id":"2305.11715","title":"A quality assurance framework for real-time monitoring of deep learning segmentation models in radiotherapy","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2312.05695","title":"The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need","created":"2023-12-09","cited_by_count":0,"area":null},{"id":"2407.18673","title":"A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2408.04170","title":"M2EF-NNs: Multimodal Multi-instance Evidence Fusion Neural Networks for Cancer Survival Prediction","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2409.19619","title":"Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noises","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2509.26027","title":"Causally Guided Gaussian Perturbations for Out-Of-Distribution Generalization in Medical Imaging","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.22994","title":"Optimizer Sensitivity In Vision Transformerbased Iris Recognition: Adamw Vs Sgd Vs Rmsprop","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2605.13148","title":"Understanding Generalization through Decision Pattern Shift","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.16298","title":"Revisiting Shape and Texture Reliance with Category-Separability-Calibrated Suppression","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.25887","title":"Device Invariance using Domain Adaptation on Acoustic Scene Classification","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.05258","title":"Grad-CAM for Vision Transformers: A Systematic Taxonomy and Audit of Methodological Ambiguity in Explainable AI","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.36448","title":"Theory on Attention Dynamics for Out-of-Distribution In-Context Learning","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00030","title":"Domain generalization and synthetic data in object detection: the enabler, the probe, and the gap","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}