{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-classification/papers/82","list_of":"/task/image-classification","task":"Image Classification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":82,"pages_in_order":105,"rows_per_page":100,"rows":[8101,8200],"of":10488,"counts":{"archive_papers_tagged":10488,"with_a_code_link":4702,"where_syntology_ran_a_sample":1392,"not_listed_spam_title":0,"listed":10488,"listed_where_code_ran":1392,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1164,"every_run_a_failure_of_syntologys_instrument":228,"listed_with_a_run_with_no_instrument_failure":1164,"listed_every_run_a_failure_of_syntologys_instrument":228,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-classification","prev":"/task/image-classification/papers/81","next":"/task/image-classification/papers/83","papers":[{"url":null,"slug":"cnn-with-large-memory-layers","title":"CNN with large memory layers","date":"2021-01-27","arxiv_id":"2101.11685","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-task-agnostic-representation-via","title":"Learning task-agnostic representation via toddler-inspired learning","date":"2021-01-27","arxiv_id":"2101.11221","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-knowledge-based-generative-zero-shot","title":"Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization","date":"2021-01-25","arxiv_id":"2101.09892","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-generalization-and-the-convex","title":"Deep Learning Generalization and the Convex Hull of Training Sets","date":"2021-01-25","arxiv_id":"2101.09849","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-data-augmentation-for-visual","title":"Spatio-temporal Data Augmentation for Visual Surveillance","date":"2021-01-25","arxiv_id":"2101.09895","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-degraded-image-classification-with","title":"Learning degraded image classification with restoration data fidelity","date":"2021-01-23","arxiv_id":"2101.09606","repositories_listed":0,"syntology":null},{"url":null,"slug":"minconvnets-a-new-class-of-multiplication","title":"MinConvNets: A new class of multiplication-less Neural Networks","date":"2021-01-23","arxiv_id":"2101.09492","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-hardware-aware","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","date":"2021-01-22","arxiv_id":"2101.09336","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-for-tabular-data","title":"Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data","date":"2021-01-20","arxiv_id":"2101.08030","repositories_listed":0,"syntology":null},{"url":"/paper/beyond-fine-tuning-classifying-high","slug":"beyond-fine-tuning-classifying-high","title":"Beyond Fine-tuning: Classifying High Resolution Mammograms using Function-Preserving Transformations","date":"2021-01-20","arxiv_id":"2101.07945","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedns-improving-federated-learning-for","title":"FedNS: Improving Federated Learning for collaborative image classification on mobile clients","date":"2021-01-20","arxiv_id":"2101.07995","repositories_listed":0,"syntology":null},{"url":null,"slug":"riemannian-based-discriminant-analysis-for","title":"Riemannian Manifold Optimization for Discriminant Subspace Learning","date":"2021-01-20","arxiv_id":"2101.08032","repositories_listed":0,"syntology":null},{"url":null,"slug":"initialization-using-perlin-noise-for","title":"Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data","date":"2021-01-19","arxiv_id":"2101.07406","repositories_listed":0,"syntology":null},{"url":null,"slug":"dissonance-between-human-and-machine","title":"Dissonance Between Human and Machine Understanding","date":"2021-01-18","arxiv_id":"2101.07337","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-methods-for-efficient","title":"Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains","date":"2021-01-18","arxiv_id":"2101.07308","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-with-limited-data","title":"Machine learning with limited data","date":"2021-01-18","arxiv_id":"2101.11461","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-do-deep-nets-learn-class-wise-patterns-1","title":"What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space","date":"2021-01-18","arxiv_id":"2101.06898","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-layer-wise-information-reinforcement","title":"A Layer-Wise Information Reinforcement Approach to Improve Learning in Deep Belief Networks","date":"2021-01-17","arxiv_id":"2101.06749","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-eosinophilic-esophagitis-diagnosis","title":"Advancing Eosinophilic Esophagitis Diagnosis and Phenotype Assessment with Deep Learning Computer Vision","date":"2021-01-13","arxiv_id":"2101.05326","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-prediction-of-alzheimer-s","title":"Deep learning based prediction of Alzheimer's disease from magnetic resonance images","date":"2021-01-13","arxiv_id":"2101.04961","repositories_listed":0,"syntology":null},{"url":null,"slug":"should-ensemble-members-be-calibrated-1","title":"Should Ensemble Members Be Calibrated?","date":"2021-01-13","arxiv_id":"2101.05397","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-the-black-box-smoothly-a","title":"Explaining the Black-box Smoothly- A Counterfactual Approach","date":"2021-01-11","arxiv_id":"2101.04230","repositories_listed":0,"syntology":null},{"url":null,"slug":"lesion2vec-deep-metric-learning-for-few-shot","title":"Lesion2Vec: Deep Metric Learning for Few-Shot Multiple Lesions Recognition in Wireless Capsule Endoscopy Video","date":"2021-01-11","arxiv_id":"2101.04240","repositories_listed":0,"syntology":null},{"url":null,"slug":"resolution-based-distillation-for-efficient","title":"Resolution-Based Distillation for Efficient Histology Image Classification","date":"2021-01-11","arxiv_id":"2101.04170","repositories_listed":0,"syntology":null},{"url":null,"slug":"spherical-transformer-adapting-spherical","title":"Spherical Transformer: Adapting Spherical Signal to CNNs","date":"2021-01-11","arxiv_id":"2101.03848","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-pretrained-cnn-feature-extractors","title":"Combining pretrained CNN feature extractors to enhance clustering of complex natural images","date":"2021-01-07","arxiv_id":"2101.02767","repositories_listed":0,"syntology":null},{"url":null,"slug":"practical-evaluation-of-out-of-distribution-1","title":"Practical Evaluation of Out-of-Distribution Detection Methods for Image Classification","date":"2021-01-07","arxiv_id":"2101.02447","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-fast-scalable-bnn-inference","title":"A Framework for Fast Scalable BNN Inference using Googlenet and Transfer Learning","date":"2021-01-04","arxiv_id":"2101.00793","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommending-accurate-and-diverse-items-using","title":"Recommending Accurate and Diverse Items Using Bilateral Branch Network","date":"2021-01-04","arxiv_id":"2101.00781","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-in-vision-a-survey","title":"Transformers in Vision: A Survey","date":"2021-01-04","arxiv_id":"2101.01169","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-modal-approach-towards-mining-social","title":"A multi-modal approach towards mining social media data during natural disasters -- a case study of Hurricane Irma","date":"2021-01-02","arxiv_id":"2101.00480","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-sensitive-activity-recognition-a","title":"Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models","date":"2021-01-02","arxiv_id":"2101.00468","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-gradient-based-kernel-approach-for","title":"A Gradient-based Kernel Approach for Efficient Network Architecture Search","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-to-analyze-and-design-the","title":"A Unified Framework to Analyze and Design the Nonlocal Blocks for Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ac-vae-learning-semantic-representation-with","title":"AC-VAE: Learning Semantic Representation with VAE for Adaptive Clustering","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"achieving-explainability-in-a-visual-hard","title":"Achieving Explainability in a Visual Hard Attention Model through Content Prediction","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-under-malicious-mislabeling","title":"Active Learning Under Malicious Mislabeling and Poisoning Attacks","date":"2021-01-01","arxiv_id":"2101.00157","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-dataset-sampling-by-deep-policy","title":"Adaptive Dataset Sampling by Deep Policy Gradient","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"afinets-attentive-feature-integration","title":"AFINets: Attentive Feature Integration Networks for Image Classification","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-view-contrastive-learning-for-few-shot","title":"Auto-view contrastive learning for few-shot image recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"baffle-towards-resolving-federated-learnings","title":"BAFFLE: TOWARDS RESOLVING FEDERATED LEARNING’S DILEMMA - THWARTING BACKDOOR AND INFERENCE ATTACKS","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-learning-to-optimize-quantifying-the","title":"Bayesian Learning to Optimize: Quantifying the Optimizer Uncertainty","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"buffer-zone-based-defense-against-adversarial","title":"Buffer Zone based Defense against Adversarial Examples in Image Classification","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"category-disentangled-context-turning","title":"Category Disentangled Context: Turning Category-irrelevant Features Into Treasures","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"certified-robustness-against-physically","title":"Certified robustness against physically-realizable patch attack via randomized cropping","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cnn-based-analysis-of-the-lurias-alternating","title":"CNN Based Analysis of the Luria’s Alternating Series Test for Parkinson’s Disease Diagnostics","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-networks","title":"Conditional Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-multiple-high-quality-deep","title":"Constructing Multiple High-Quality Deep Neural Networks: A TRUST-TECH Based Approach","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"context-agnostic-learning-using-synthetic","title":"Context-Agnostic Learning Using Synthetic Data","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"counterfactual-thinking-for-long-tailed","title":"Counterfactual Thinking for Long-tailed Information Extraction","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/deep-repulsive-clustering-of-ordered-data","slug":"deep-repulsive-clustering-of-ordered-data","title":"Deep Repulsive Clustering of Ordered Data Based on Order-Identity Decomposition","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"demystifying-loss-functions-for","title":"Demystifying Loss Functions for Classification","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-residues-of-cosmic-events-using","title":"Detecting residues of cosmic events using residual neural network","date":"2021-01-01","arxiv_id":"2101.00195","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-booster-training-a-detection","title":"Detection Booster Training: A detection booster training method for improving the accuracy of classifiers.","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diet-snn-a-low-latency-spiking-neural-network","title":"DIET-SNN: A Low-Latency Spiking Neural Network with Direct Input Encoding & Leakage and Threshold Optimization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-invariant-disentangled-network-for","title":"Domain-Invariant Disentangled Network for Generalizable Object Detection","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-tree-wavelet-packet-cnns-for-image","title":"Dual-Tree Wavelet Packet CNNs for Image Classification","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-constrained-self-training-for","title":"Energy-constrained Self-training for Unsupervised Domain Adaptation","date":"2021-01-01","arxiv_id":"2101.00316","repositories_listed":0,"syntology":null},{"url":null,"slug":"explicit-connection-distillation","title":"Explicit Connection Distillation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-target-driven-image-classification","title":"Exploring Target Driven Image Classification","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feedforward-legendre-memory-unit","title":"Feedforward Legendre Memory Unit","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"general-adversarial-defense-via-pixel-level","title":"General Adversarial Defense via Pixel Level and Feature Level Distribution Alignment","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-structural-aggregation-for-explainable","title":"Graph Structural Aggregation for Explainable Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-accuracy-of-neural-networks-in","title":"Improving the accuracy of neural networks in analog computing-in-memory systems by a generalized quantization method","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-methods-in-hyperbolic-spaces","title":"Kernel Methods in Hyperbolic Spaces","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-multiscale-wavelet-superpixels","title":"Learning from multiscale wavelet superpixels using GNN with spatially heterogeneous pooling","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-representation-in-colour-conversion","title":"Learning Representation in Colour Conversion","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/learning-the-connections-in-direct-feedback","slug":"learning-the-connections-in-direct-feedback","title":"Learning the Connections in Direct Feedback Alignment","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lipschitz-bounded-equilibrium-networks","title":"Lipschitz-Bounded Equilibrium Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"llboost-last-layer-perturbation-to-boost-pre","title":"LLBoost: Last Layer Perturbation to Boost Pre-trained Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-categorical-cross-entropy-mcce-a","title":"Maximum Categorical Cross Entropy (MCCE): A noise-robust alternative loss function to mitigate racial bias in Convolutional Neural Networks (CNNs) by reducing overfitting","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moco-pretraining-improves-representations-and","title":"MoCo-Pretraining Improves Representations and Transferability of Chest X-ray Models","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"more-side-information-better-pruning-shared","title":"More Side Information, Better Pruning: Shared-Label Classification as a Case Study","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"near-optimal-glimpse-sequences-for-training","title":"Near-Optimal Glimpse Sequences for Training Hard Attention Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neighbor-class-consistency-on-unsupervised","title":"Neighbor Class Consistency on Unsupervised Domain Adaptation","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nonconvex-continual-learning-with-episodic","title":"Nonconvex Continual Learning with Episodic Memory","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nose-augment-fast-and-effective-data","title":"NOSE Augment: Fast and Effective Data Augmentation Without Searching","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effectiveness-of-deep-ensembles-for","title":"On the Effectiveness of Deep Ensembles for Small Data Tasks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-inductive-bias-of-a-cnn-for","title":"On the Inductive Bias of a CNN for Distributions with Orthogonal Patterns","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-allocation-of-data-across-training","title":"Optimal allocation of data across training tasks in meta-learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"p-swish-activation-function-with-learnable","title":"P-Swish: Activation Function with Learnable Parameters Based on Swish Activation Function in Deep Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parameterized-pseudo-differential-operators","title":"Parameterized Pseudo-Differential Operators for Graph Convolutional Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-driven-attack-learning-to-query-for","title":"Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"protecting-dnns-from-theft-using-an-ensemble","title":"Protecting DNNs from Theft using an Ensemble of Diverse Models","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-task-complexity-through","title":"Quantifying Task Complexity Through Generalized Information Measures","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-implicit-bias-in-latent-domain","title":"Reducing Implicit Bias in Latent Domain Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/robust-early-learning-hindering-the","slug":"robust-early-learning-hindering-the","title":"Robust early-learning: Hindering the memorization of noisy labels","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"romul-scale-adaptative-population-based","title":"ROMUL: Scale Adaptative Population Based Training","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sparsifying-networks-via-subdifferential","title":"Sparsifying Networks via Subdifferential Inclusion","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"student-customized-knowledge-distillation","title":"Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesized-feature-based-few-shot-class","title":"Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-bootstrap-framework-generalization","title":"The Bootstrap Framework: Generalization Through the Lens of Online Optimization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-foes-of-neural-networks-data-efficiency","title":"The Foes of Neural Network’s Data Efficiency Among Unnecessary Input Dimensions","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-simpler-the-better-vanilla-sgd-revisited","title":"The simpler the better: vanilla sgd revisited","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/toward-understanding-supervised","slug":"toward-understanding-supervised","title":"Toward Understanding Supervised Representation Learning with RKHS and GAN","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/towards-practical-second-order-optimization","slug":"towards-practical-second-order-optimization","title":"Towards Practical Second Order Optimization for Deep Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"twindnn-a-tale-of-two-deep-neural-networks","title":"TwinDNN: A Tale of Two Deep Neural Networks","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertain-out-of-domain-generalization","title":"Uncertain Out-of-Domain Generalization","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-calibration-error-a-new-metric","title":"Uncertainty Calibration Error: A New Metric for Multi-Class Classification","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-adaptation-via-minimized","title":"Unsupervised Domain Adaptation via Minimized Joint Error","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"8b5bd080bfb644d3298044d6028233aba9cf8659bb1d4aaa94110bf3da12203e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}