Skip to content

Latest commit

 

History

History
535 lines (446 loc) · 25.2 KB

Zero-Shot.md

File metadata and controls

535 lines (446 loc) · 25.2 KB

Contents

Zero-Shot Learning

Surveys

  • Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey (Arxiv 2022) [Paper]

  • A Survey of Zero-shot Generalisation in Deep Reinforcement Learning (JAIR 2023) [Paper]

  • Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval (ICMLA 2021) [Paper]

  • Knowledge-aware Zero-Shot Learning: Survey and Perspective (IJCAI 2021 Survey Track) [Paper]

  • A Survey of Deep Learning for Low-Shot Object Detection (Arxiv 2022) [Paper]

  • Weak Novel Categories without Tears: A Survey on Weak-Shot Learning (Arxiv 2021) [Paper]

2023 Papers

CVPR

  • Learning Attention as Disentangler for Compositional Zero-shot Learning (CVPR 2023) [Paper]

  • Delving into Shape-aware Zero-shot Semantic Segmentation (CVPR 2023) [Paper]

ICLR

  • Relative representations enable zero-shot latent space communication (ICLR 2023 top 5%) [Paper]
    Datasets: MNIST, F-MNIST, CIFAR-10, CIFAR-100, Cora, CiteSeer, PubMed, Amazon Reviews, TREC, DBpedia
    Task: Image Classification, Graph Node Classification, Image reconstruction, Text Classification

WACV

  • Zero-Shot Versus Many-Shot: Unsupervised Texture Anomaly Detection (WACV 2023) [Paper] [Code]
    Datasets: MVTec
    Task: Texture Anomaly Detection

  • Learning Attention Propagation for Compositional Zero-Shot Learning (WACV 2023) [Paper]
    Datasets: MIT-States, CGQA, UT-Zappos
    Task: Image Classification

  • InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images (WACV 2023) [Paper]
    Datasets: Synthetic Cars, Cars196
    Task: Deep Metric Learning Images

2022 Papers

CVPR

  • KG-SP: Knowledge Guided Simple Primitivesfor Open World Compositional Zero-Shot Learning (CVPR 2022) [Paper] [Code]
    Datasets: UT-Zappos, MIT-States, C-GQA
    Task: Compositional Zero-Shot Learning

  • Unseen Classes at a Later Time? No Problem (CVPR 2022) [Paper]
    Datasets: AWA1 and AWA2, Attribute Pascal and Yahoo(aPY), Caltech-UCSD-Birds 200-2011 (CUB) and SUN
    Task: Image Classification

  • Few-Shot Keypoint Detection With Uncertainty Learning for Unseen Species (CVPR 2022) [Paper]
    Datasets: Animal pose, CUB, NABird
    Task: Keypoint Detection

  • Distinguishing Unseen From Seen for Generalized Zero-Shot Learning (CVPR 2022) [Paper]
    Datasets: Caltech-UCSD Birds-200-2011 (CUB), Ox-ford Flowers (FLO), SUN Attribute (SUN), Animals with Attributes 1 (AwA1) and Animals with Attributes 2(AwA2)
    Task: Image Classification

  • Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning (CVPR 2022) [Paper] [Code]
    Datasets: MIT-States, UT-Zappos, and C-GQA
    Task: Image Classification

  • ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic (CVPR 2022) [Paper] [Code]
    Datasets: COCO
    Task: Image Captioning

  • LiT: Zero-Shot Transfer With Locked-Image Text Tuning (CVPR 2022) [Paper]
    Datasets: CC12M; YFCC100m; ALIGN; ImageNet-v2, -R, -A, -ReaL, and ObjectNet, VTAB; Cifar100; Pets; Wikipedia based Image Text (WIT)
    Task: Image-Text Retreival

  • Non-Generative Generalized Zero-Shot Learning via Task-Correlated Disentanglement and Controllable Samples Synthesis (CVPR 2022) [Paper]
    Datasets: Animal with Attribute (AWA1), Animal with Attribute2 (AWA2), Caltech-UCSD Birds-200-2011(CUB), Oxford 102 flowers (FLO)
    Task: Image Classification

  • CLIP-Forge: Towards Zero-Shot Text-To-Shape Generation (CVPR 2022) [Paper] [Code]
    Datasets: ShapeNet(v2) dataset
    Task: Text-To-Shape Generation

  • Zero-Shot Text-Guided Object Generation With Dream Fields (CVPR 2022) [Paper] [Code]
    Datasets: COCO
    Task: Text-Guided Object Generation

  • En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning (CVPR 2022) [Paper]
    Datasets: AWA1, AWA2, CUB, OxfordFlowers (FLO), Attributes Pascal and Yahoo(APY)
    Task: Image Classification

  • VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning (CVPR 2022) [Paper] [Code]
    Datasets: AWA2; CUB; SUN
    Task: Image Classification

  • Sketch3T: Test-Time Training for Zero-Shot SBIR (CVPR 2022) [Paper]
    Datasets: Sketchy; TU-Berlin Extension
    Task: Sketch-Based Image Retrieval

  • MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning (CVPR 2022) [Paper] [Code]
    Datasets: CUB (Caltech UCSD Birds 200), SUN (SUN Attribute) and AWA2 (Animals with Attributes 2)
    Task: Image Classification

  • Decoupling Zero-Shot Semantic Segmentation (CVPR 2022) [Paper] [Code]
    Datasets: PASCAL VOC; COCO-Stuff
    Task: Semantic Segmentation

  • Robust Region Feature Synthesizer for Zero-Shot Object Detection (CVPR 2022) [Paper]
    Datasets: PASCAL VOC, COCO, and DIOR
    Task: Object Detection

  • IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization (CVPR 2022) [Paper] [Code]
    Datasets: CIFAR-10/100; ImageNet
    Task: Zero-Shot Quantization

  • It's All in the Teacher: Zero-Shot Quantization Brought Closer to the Teacher (CVPR 2022) [Paper]
    Datasets: CIFAR-10/100; ImageNet
    Task: Zero-Shot Quantization

  • Robust Fine-Tuning of Zero-Shot Models (CVPR 2022) [Paper]
    Datasets: ImageNet distribution shifts (ImageNetV2, ImageNet-R,ObjectNet, and ImageNet-A, ImageNet Sketch); CIFAR10.1 &10.2
    Task: Zero-Shot Distribution Shift Robustness

  • Neural Mean Discrepancy for Efficient Out-of-Distribution Detection (CVPR 2022) [Paper]
    Datasets: CIFAR-10, CIFAR-100, SVHN, croppedImageNet, cropped LSUN, iSUN, and Texture
    Task: Image Classification

NeurIPS

  • Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis (NeurIPS 2022) [Paper] [Code]
    Datasets: Caltech-UCSD Birds-200-2011 (CUB Dataset), α-CLEVR
    Task: Image Classification

  • PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories (NeurIPS 2022) [Paper] [Code]
    Datasets: ShapeNet, ScanNet, Scan2CAD
    Task: 3D Shape Reconstruction

  • Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation (NeurIPS 2022) [Paper] [Code]
    Datasets: Pascal VOC and ADE20K
    Task: Continual Image Classification

ECCV

  • Zero-Shot Attribute Attacks on Fine-Grained Recognition Models (ECCV 2022) [Paper]
    Datasets: Caltech-UCSD Birds-200-2011(CUB), Animal with Attributes (AWA2) and SUN Attribute (SUN)
    Task: Image Classification

  • Zero-Shot Learning for Reflection Removal of Single 360-Degree Image (ECCV 2022) [Paper]
    Datasets: 30 test 360-degree images
    Task: Reflection Removal

  • Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification (ECCV 2022) [Paper] [Code]
    Datasets: ImageNet-21K-D (D for Directed Acyclic Graph)
    Task: Image Classification

  • Learning Invariant Visual Representations for Compositional Zero-Shot Learning (ECCV 2022) [Paper] [Code]
    Datasets: Mit-States; UT-Zappos50K; Clothing16K, and AO-CLEVr
    Task: Image Retrieval

  • 3D Compositional Zero-Shot Learning with DeCompositional Consensus (ECCV 2022) [Paper]
    Datasets: Compositional PartNet (C-PartNet)
    Task: Compositional Zero-Shot Segmentation

  • Zero-Shot Category-Level Object Pose Estimation (ECCV 2022) [Paper] [Code]
    Datasets: Common Objects in 3D (CO3D); PoseContrast
    Task: Object Pose Estimation

AAAI

  • Open Vocabulary Electroencephalography-to-Text Decoding and Zero-Shot Sentiment Classification (AAAI 2022) [Paper] [Code]
    Datasets: ZuCo
    Task: Brain Signals Language Decoding

CVPRw

  • Semantically Grounded Visual Embeddings for Zero-Shot Learning (CVPRw 2022) [Paper]
    Datasets: CUB(312−d), AWA(85−d) and aPY(64−d); FLO
    Task: Semantic Embeddings

  • Zero-Shot Learning Using Multimodal Descriptions (CVPRw 2022) [Paper]
    Datasets: CUB-200-2011 (CUB), SUN attributes (SUN) and DeepFashion (DF)
    Task: Multimodal Zero-Shot

WACV

  • COCOA: Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains (WACV 2022) [Paper]
    Datasets: DomainNet, DomainNet-LS
    Task: Domain Generalization and Novel Class Discovery

2021 Papers

CVPR

  • Counterfactual Zero-Shot and Open-Set Visual Recognition (CVPR 2021) [Paper]
    Datasets: MNIST, SVHN,CIFAR10 and CIFAR100
    Task: Object Detection

ICCV

  • Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation (ICCV 2021) [Paper]
    Datasets: Pascal VOC 2012, Pascal Context
    Task: Semantic Segmentation

BMVC

  • Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains (BMVC 2021) [Paper]
    Datasets: DomainNet, DomainNet-LS
    Task: Domain Generalization

2020 Papers

CVPR

  • Discovering Human Interactions With Novel Objects via Zero-Shot Learning (CVPR 2020) [Paper] [Code]
    Datasets: V-COCO, HICO-DET
    Task: Human Object Interaction

ICLR

  • Locality and Compositionality in Zero-Shot Learning (ICLR 2020) [Paper]
    Datasets: AwA2, CUB-200-2011
    Task: Image Classification

  • Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories (ICLR 2020) [Paper] [Code]
    Datasets: PartNet
    Task: 3D Part Discovery

ICML

  • Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data (ICML 2020) [Paper] [Code]
    Datasets: MNIST, CIFAR10
    Task: Image Classification

  • Hallucinative Topological Memory for Zero-Shot Visual Planning (ICML 2020) [Paper]
    Datasets: Mujoco simulation (Block wall, Block wall with complex obstacle, Block insertion, Robot manipulation)
    Task: Visual Planning

  • “Other-Play” for Zero-Shot Coordination (ICML 2020) [Paper] [Code]
    Datasets: “lever game”, Hanabi with AI Agents
    Task: Zero-Shot Coordination

ECCV

  • A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning (ECCV 2020) [Paper]
    Datasets: AWA1, AWA2, CUB, FLO and SUN
    Task: Out-of-Distribution Image Classification

  • Towards Recognizing Unseen Categories in Unseen Domains (ECCV 2020) [Paper] [Code]
    Datasets: AWA, CUB, FLO and SUN, PACS
    Task: Out-of-Distribution Image Classification

Older Papers

  • Generalized Zero-shot Learning using Open Set Recognition (BMVC 2019) [Paper]
    Datasets: AWA1, APY, FLO, and CUB
    Task: Image Classification

  • Image Captioning with Unseen Objects (BMVC 2019) [Paper]
    Datasets: COCO
    Task: Image Captioning

  • Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning (NeurIPS 2018) [Paper]
    Datasets: CUB and NABird
    Task: Image Classification

  • MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning (ICML 2018) [Paper]
    Datasets: Animals with Attributes (AwA), Caltech-UCSD Birds-200-2011 (CUB) and ImageNet 2012/2010
    Task: Image Classification

  • Zero-Shot Visual Imitation (ICLR 2018 Oral) [Paper] [Code]
    Datasets: Rope manipulation using Baxter robot, Navigation of a wheeled robot in cluttered office environments, Simulated 3D navigation
    Task: Imitation Learning

Zero-Shot Learning Videos

Surveys

  • Zero-Shot Action Recognition in Videos: A Survey (Neurocomputing 2021) [Paper]

  • A Review of Generalized Zero-Shot Learning Methods (TPAMI 2022) [Paper]

  • Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data (Arxiv 2017) [Paper]

2023 Papers

WACV

  • Language-Free Training for Zero-Shot Video Grounding (WACV 2023) [Paper]
    Datasets: Charades-STA, ActivityNet Captions
    Task: Video Grounding

  • Semantics Guided Contrastive Learning of Transformers for Zero-Shot Temporal Activity Detection (WACV 2023) [Paper]
    Datasets: Thumos’14 and Charades
    Task: Action Recognition

2022 Papers

CVPR

  • Uni-Perceiver: Pre-Training Unified Architecture for Generic Perception for Zero-Shot and Few-Shot Tasks (CVPR 2022) [Paper]
    Datasets: ImageNet-21k; Kinetics-700 and Moments in Time; BookCorpora & English Wikipedia (Books&Wiki) and PAQ; COCO Caption, SBUCaptions (SBU), Visual Genome, CC3M, CC12M and YFCC; Flickr30k, MSVD,VQA ,and GLUE
    Task: Image-Text Retreival; Image and Video Classification

  • Cross-Modal Representation Learning for Zero-Shot Action Recognition (CVPR 2022) [Paper] [Code]
    Datasets: Kinetics -> UCF101, HMDB51, and ActivityNet
    Task: Action Recognition

  • Audio-Visual Generalised Zero-Shot Learning With Cross-Modal Attention and Language (CVPR 2022) [Paper] [Code]
    Datasets: VGGSound; UCF101; ActivityNet
    Task: Action Recognition

  • Alignment-Uniformity Aware Representation Learning for Zero-Shot Video Classification (CVPR 2022) [Paper] [Code]
    Datasets: Kinetics-700 -> UCF101, HMDB51
    Task: Action Recognition

ECCV

  • Temporal and cross-modal attention foraudio-visual zero-shot learning (ECCV 2022) [Paper] [Code]
    Datasets: UCF-GZSL^cls, VGGSound-GZSL^cls, and ActivityNet-GZSL^cls1
    Task: Action Recognition

  • CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition (ECCV 2022) [Paper] [Code]
    Datasets: Olympic Sports; UCF-101; HMDB-51
    Task: Action Recognition

  • Rethinking Zero-Shot Action Recognition: Learning from Latent Atomic Actions (ECCV 2022) [Paper]
    Datasets: KineticsZSAR, HMDB51, and UCF101
    Task: Action Recognition

  • Zero-Shot Temporal Action Detection via Vision-Language Prompting (ECCV 2022) [Paper] [Code]
    Datasets: THUMOS14; ActivityNet v1.3
    Task: Temporal Action Detection (TAD)

2021 Papers

CVPR

  • Recognizing Actions in Videos From Unseen Viewpoints (CVPR 2021) [Paper]
    Datasets: Human3.6M, MLB-YouTube, Toyota SmartHome (TSH), NTU-RGB-D
    Task: Action Recognition

BMVC

  • Zero-Shot Action Recognition from Diverse Object-Scene Compositions (BMVC 2021) [Paper] [Code]
    Datasets: UCF-101, Kinetics-400
    Task: Action Recognition

Older Papers

  • Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition (CVPR 2019) [Paper] [Code]
    Datasets: Olympic Sports, HMDB51 and UCF101
    Task: Action Recognition