Few- /Zero-Shot Paper List
CVPR 2022
- Zero-Shot Text-Guided Object Generation with Dream Fields
- Few-Shot Incremental Learning for Label-to-Image Translation
- Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
- Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning
- Balanced and Hierarchical Relation Learning for One-shot Object Detection
- Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
- Few-Shot Font Generation by Learning Fine-Grained Local Styles
- Distinguishing Unseen from Seen for Generalized Zero-shot Learning
- Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
- Task-Adaptive Negative Envision for Few-Shot Open-Set Recognition
- Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis
- Forward Compatible Few-Shot Class-Incremental Learning
- Ranking Distance Calibration for Cross-Domain Few-Shot Learning
- Learning to Memorize Feature Hallucination for One-Shot Image Generation
- Improving Adversarially Robust Few-shot Image Classification with Generalizable Representations
- En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
- Few-Shot Object Detection with Fully Cross-Transformer
- FS6D: Few-Shot 6D Pose Estimation of Novel Objects
- Generating Representative Samples for Few-Shot Classification
- Task Discrepancy Maximization for Fine-grained Few-Shot Classification
- EASE: Unsupervised Discriminant Subspace Learning for Transductive
- A Closer Look at Few-shot Image Generation
- Motion-modulated Temporal Fragment Alignment Network For Few-Shot Action Recognition
- VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
- Sketch3T: Test-Time Training for Zero-Shot SBIR
- Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language
- Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection
- Integrative Few-Shot Learning for Classification and Segmentation
- Constrained Few-shot Class-incremental Learning
- iFS-RCNN: An Incremental Few-shot Instance Segmenter
- Cross-domain Few-shot Learning with Task-specific Adapters
- OnePose: One-Shot Object Pose Estimation without CAD Models
- Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
- GANORCON: Are Generative Models Useful for Few-shot Segmentation?
- MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning
- Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer
- Few-shot Learning with Noisy Labels
- Semantic-aligned Fusion Transformer for One-shot Object Detection
- Robust Region Feature Synthesizer for Zero-Shot Object Detection
- It’s All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
- OSOP: A Multi-Stage One Shot Object Pose Estimation Framework
- Robust fine-tuning of zero-shot models
- Matching Feature Sets for Few-Shot Image Classification
- XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
- Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
- Learning What Not to Segment: A New Perspective on Few-Shot Segmentation
- KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
- Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification
- Few-Shot Head Swapping in the Wild
- Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment
- CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification
- Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation
- Generalized Few-shot Semantic Segmentation
- Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator
- MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning
- Semi-Supervised Few-shot Learning via Multi-Factor Clustering
- InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
- Label, Verify, Correct: A Simple Few Shot Object Detection Method
- Decoupling Zero-Shot Semantic Segmentation
- Multi-modal Extreme Classification
- Few-shot Backdoor Defense Using Shapley Estimation
- Attribute Group Editing for Reliable Few-shot Image Generation
- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
- A Hybrid Egocentric Activity Anticipation Framework via Memory-Augmented Recurrent and One-shot Representation Forecasting
- Learning Non-target Knowledge for Few-shot Semantic Segmentation
- Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions
- ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic
- LiT: Zero-Shot Transfer with Locked-image text Tuning
- Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
- CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation
- Quantization-aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging
- Which images to label for few-shot medical landmark detection?
- HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet
- Kernelized Few-shot Object Detection with Efficient Integral Aggregation
- Cross-modal Representation Learning for Zero-shot Action Recognition
- Acquiring a Dynamic Light Field through a Single-Shot Coded Image
- Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
- HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging
- Hybrid Relation Guided Set Matching for Few-shot Action Recognition
- Spatio-temporal Relation Modeling for Few-shot Action Recognition
- YouMVOS: An Actor-centric Multi-shot Video Object Segmentation Dataset
- Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species
ACL 2022
Long Papers
- JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection
- Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation
- FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding
- Learn to Adapt for Generalized Zero-Shot Text Classification
- Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization
- Few-Shot Class-Incremental Learning for Named Entity Recognition
- Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension
- On The Ingredients of an Effective Zero-shot Semantic Parser
- Few-Shot Tabular Data Enrichment Using Fine-Tuned Transformer Architectures
- Generating Scientific Claims for Zero-Shot Scientific Fact Checking
- Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
- Prompt-free and Efficient Few-shot Learning with Language Models
- Neural Pipeline for Zero-Shot Data-to-Text Generation
- Zero-Shot Cross-lingual Semantic Parsing
- Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents
- Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction
- Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting
- ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension
- Noisy Channel Language Model Prompting for Few-Shot Text Classification
- Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models
- Few-shot Named Entity Recognition with Self-describing Networks
- Pre-training to Match for Unified Low-shot Relation Extraction
- CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment
- AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
- CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
- Substructure Distribution Projection for Zero-Shot Cross-Lingual Dependency Parsing
- Prototypical Verbalizer for Prompt-based Few-shot Tuning
- Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings
- Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
- Label Semantic Aware Pre-training for Few-shot Text Classification
- PPT: Pre-trained Prompt Tuning for Few-shot Learning
- Few-Shot Learning with Siamese Networks and Label Tuning
- FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning
- End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding
Short Papers
- Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension
- LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory
- Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
Findings
- RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction
- Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning
- Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation
- Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging
- A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction
- A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking
- Decomposed Meta-Learning for Few-Shot Named Entity Recognition
- N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
- Label Semantics for Few Shot Named Entity Recognition
- Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble](https://aclanthology.org/2022.findings-acl.166/)
- Hierarchical Recurrent Aggregative Generation for Few-Shot NLG
- Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models
- OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval
- LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval
- EICO: Improving Few-Shot Text Classification via Explicit and Implicit Consistency Regularization
- Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking
- Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
- A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation
- CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding
- Improving Zero-Shot Cross-lingual Transfer Between Closely Related Languages by Injecting Character-Level Noise
- Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
本博客所有文章除特别声明外,均采用 CC BY-NC-SA 4.0 许可协议。转载请注明来自 Xuan Feng's homepage!