REVIEW 19 cited by
Learning from Few Examples: A Summary of Approaches to Few-Shot Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. Requiring a large number of data samples, many deep learning solutions suffer from data hunger and extensively high computation time and resources. Furthermore, data is often not available due to not only the nature of the problem or privacy concerns but also the cost of data preparation. Data collection, preprocessing, and labeling are strenuous human tasks. Therefore, few-shot learning that could drastically reduce the turnaround time of building machine learning applications emerges as a low-cost solution. This survey paper comprises a representative list of recently proposed few-shot learning algorithms. Given the learning dynamics and characteristics, the approaches to few-shot learning problems are discussed in the perspectives of meta-learning, transfer learning, and hybrid approaches (i.e., different variations of the few-shot learning problem).
Forward citations
Cited by 19 Pith papers
-
Test-Time Scaling via Error Localization
TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.
-
SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair
A three-agent locate-suggest-fix framework with a knowledge-graph toolkit resolves 154/300 SWE-Bench-Lite issues with Claude-3.5, outperforming same-model baselines by 5-10 points.
-
Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment
For few-shot surgical skill assessment, pre-training on small but domain-relevant surgery videos outperforms large-scale, less aligned datasets, and mixing procedure-specific data only helps when the external source i...
-
Automatic Metadata Extraction for Text-to-SQL
LLM-generated summaries of database profiling statistics outperform human-written metadata for text-to-SQL on BIRD, and a SQL-generation-based schema linker adds further gains.
-
Communication Styles and Reader Preferences of LLM and Human Experts in Explaining Health Information
LLM-generated health fact-checking articles score lower on expert-style communication metrics but are preferred by lay readers, suggesting structured presentation may outweigh traditional quality cues.
-
"It was Mentally Painful to Try and Stop": Design Opportunities for Just-in-Time Interventions for People with Obsessive-Compulsive Disorder in the Real World
An interview study identifies trigger properties, compulsion patterns, and coping-strategy conflicts that should shape future just-in-time OCD self-management technologies.
-
ASSERTIFY: Utilizing Large Language Models to Generate Assertions for Production Code
A prompt-engineered LLM pipeline can generate production code assertions with up to 83.5% compile accuracy and 0.526 ROUGE-L similarity to developer-written assertions.
-
Advancing Image-Based Grapevine Variety Classification with a New Benchmark and Evaluation of Masked Autoencoders
MAE self-supervised pre-training on 54,571 unlabeled grapevine images improves downstream 43-class variety classification (F1 0.7956) over ImageNet-initialized baselines, and the paper releases two multi-season labele...
-
Frame-Level Real-Time Assessment of Stroke Rehabilitation Exercises from Video-Level Labeled Data: Task-Specific vs. Foundation Models
Using gradient saliency and pretrained video/time-series models, frame-level stroke exercise quality can be learned from video-level labels, with the best configuration reaching 72% AUC versus 69% for a ground-truth-t...
-
Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving
MATH-VF formalizes LLM math solutions into SimpleMath and uses a tool-augmented critic to verify each reasoning step and offer corrective feedback.
-
On the effective transfer of knowledge from English to Hindi Wikipedia
A retrieval, neutralization, and machine-translation pipeline can add relevant factual text to Hindi Wikipedia biography sections, but the claimed 65% and 62% gains are not fully supported by the reported evaluation.
-
SAM$^{*}$: Task-Adaptive SAM with Physics-Guided Rewards
Reward-guided hyperparameter search turns SAM into a task-specific microscope-particle segmenter, with validation limited to single images and no ground truth.
-
Machine Learning Methods for Small Data and Upstream Bioprocessing Applications: A Comprehensive Review
The paper's new contribution is a taxonomy that organizes small-data ML methods by ML lifecycle stage rather than by technique.
-
Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks
A multi-metric prototypical network reports improved few-shot intrusion detection on three datasets, but the gains rest on per-dataset hand-picked metric weights and no held-out unseen-attack test.
-
Aspect-Based Few-Shot Learning
A permutation-invariant module that derives a support-set-dependent masking aspect improves matching in a synthetic aspect-based few-shot learning setting.
-
Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements
Generating fixes with GPT-3.5 Turbo and GPT-4o, prompted with SonarQube findings and web-retrieved examples, removed most flagged bugs, vulnerabilities, and code smells from one codebase, with success judged solely by...
-
Anomaly Detection for Industrial Applications, Its Challenges, Solutions, and Future Directions: A Review
A structured survey of vision-based industrial anomaly detection covering acquisition, preprocessing, learning, evaluation, datasets, and future directions; no new result.
-
Hyperspectral Imaging-Based Grain Quality Assessment With Limited Labelled Data
A prototypical few-shot network with pre-computed class prototypes reaches 97.75 percent accuracy on eight grain types using 2,880 training images, close to the 99.75 percent of a model trained on 16,666 images.
-
Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact
A broad survey arguing that AGI requires modular, memory-augmented, embodied architectures rather than scaled-up token prediction, with a brief proposal to decompose intelligence into five components.
Discussion (0). Continue with ORCID to comment.