{"list":"other","total":96,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1704.03976","title":"Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning","created":"2017-04-13","cited_by_count":920},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2104.08315","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","created":"2021-04-16","cited_by_count":263},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"1912.12854","title":"Pareto Multi-Task Learning","created":"2019-12-30","cited_by_count":224},{"id":"1802.08735","title":"A DIRT-T Approach to Unsupervised Domain Adaptation","created":"2018-02-23","cited_by_count":215},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155},{"id":"2003.08607","title":"Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering","created":"2020-03-19","cited_by_count":140},{"id":"2003.12237","title":"Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations","created":"2020-03-27","cited_by_count":133},{"id":"2003.13183","title":"Gradually Vanishing Bridge for Adversarial Domain Adaptation","created":"2020-03-30","cited_by_count":130},{"id":"2108.02818","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","created":"2021-08-05","cited_by_count":128},{"id":"2202.06687","title":"Domain Adaptation via Prompt Learning","created":"2022-02-14","cited_by_count":128},{"id":"2010.04104","title":"Learning the Pareto Front with Hypernetworks","created":"2020-10-08","cited_by_count":125},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1904.04663","title":"Domain-Symmetric Networks for Adversarial Domain Adaptation","created":"2019-04-09","cited_by_count":120},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"1803.00830","title":"Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift","created":"2018-03-02","cited_by_count":109},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"2206.08213","title":"A Closer Look at Smoothness in Domain Adversarial Training","created":"2022-06-16","cited_by_count":85},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83},{"id":"2010.04925","title":"Regularizing Neural Networks via Adversarial Model Perturbation","created":"2020-10-10","cited_by_count":78},{"id":"1911.11554","title":"Multi-source Distilling Domain Adaptation","created":"2019-11-22","cited_by_count":73},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63},{"id":"2110.12024","title":"A Prototype-Oriented Framework for Unsupervised Domain Adaptation","created":"2021-10-22","cited_by_count":62},{"id":"2207.07180","title":"Contrastive Adapters for Foundation Model Group Robustness","created":"2022-07-14","cited_by_count":62},{"id":"2308.05659","title":"AD-CLIP: Adapting Domains in Prompt Space Using CLIP","created":"2023-08-10","cited_by_count":62},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60},{"id":"2006.16434","title":"Efficient Continuous Pareto Exploration in Multi-Task Learning","created":"2020-06-29","cited_by_count":57},{"id":"2307.00764","title":"Hierarchical Open-vocabulary Universal Image Segmentation","created":"2023-07-03","cited_by_count":54},{"id":"1911.07982","title":"Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling","created":"2019-11-18","cited_by_count":53},{"id":"2007.08801","title":"Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation","created":"2020-07-17","cited_by_count":53},{"id":"1912.10405","title":"Adversarial Cross-Domain Action Recognition with Co-Attention","created":"2019-12-22","cited_by_count":51},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44},{"id":"2005.06717","title":"Domain Conditioned Adaptation Network","created":"2020-05-14","cited_by_count":43},{"id":"2103.11169","title":"Your Classifier can Secretly Suffice Multi-Source Domain Adaptation","created":"2021-03-20","cited_by_count":42},{"id":"2201.01003","title":"Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources","created":"2022-01-04","cited_by_count":42},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39},{"id":"2306.04949","title":"Robust Learning with Progressive Data Expansion Against Spurious Correlation","created":"2023-06-08","cited_by_count":39},{"id":"2403.02899","title":"Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation","created":"2024-03-05","cited_by_count":32},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30},{"id":"2202.10725","title":"Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain","created":"2022-02-22","cited_by_count":28},{"id":"2004.01377","title":"Sequential Learning for Domain Generalization","created":"2020-04-03","cited_by_count":26},{"id":"2209.15210","title":"Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation","created":"2022-09-30","cited_by_count":25},{"id":"2107.14447","title":"T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation","created":"2021-07-30","cited_by_count":24},{"id":"2105.10843","title":"Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation","created":"2021-05-23","cited_by_count":20},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17},{"id":"2210.12360","title":"Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models","created":"2022-10-22","cited_by_count":16},{"id":"2111.13822","title":"On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources","created":"2021-11-27","cited_by_count":15},{"id":"2210.00706","title":"Information-Theoretic Analysis of Unsupervised Domain Adaptation","created":"2022-10-03","cited_by_count":15},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15},{"id":"2206.01934","title":"Stochastic Multiple Target Sampling Gradient Descent","created":"2022-06-04","cited_by_count":14},{"id":"2401.14148","title":"LanDA: Language-Guided Multi-Source Domain Adaptation","created":"2024-01-25","cited_by_count":13},{"id":"2004.12529","title":"Towards Accurate and Robust Domain Adaptation under Noisy Environments","created":"2020-04-27","cited_by_count":12},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12},{"id":"2203.00553","title":"Global-Local Regularization Via Distributional Robustness","created":"2022-03-01","cited_by_count":11},{"id":"2211.10691","title":"Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States","created":"2022-11-19","cited_by_count":11},{"id":"2303.09165","title":"A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation","created":"2023-03-16","cited_by_count":11},{"id":"2403.02695","title":"Controllable Prompt Tuning For Balancing Group Distributional Robustness","created":"2024-03-05","cited_by_count":10},{"id":"2401.15741","title":"SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks","created":"2024-01-28","cited_by_count":7},{"id":"2302.11984","title":"Unsupervised Domain Adaptation via Distilled Discriminative Clustering","created":"2023-02-23","cited_by_count":5},{"id":"2305.10713","title":"Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency","created":"2023-05-18","cited_by_count":5}],"next_cursor":null}