SOTAVerified

zero-shot-classification

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 422 papers

TitleStatusHype
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image ClassificationCode1
CLIPArTT: Adaptation of CLIP to New Domains at Test TimeCode1
Modeling Caption Diversity in Contrastive Vision-Language PretrainingCode1
OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned ImagesCode1
Knowledge-enhanced Visual-Language Pretraining for Computational PathologyCode1
Label Propagation for Zero-shot Classification with Vision-Language ModelsCode1
VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Human Annotation-Free Pathological Image ClassificationCode1
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance SegmentationCode1
MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social DiscussionsCode1
CLIP-Guided Source-Free Object Detection in Aerial ImagesCode1
Improved Zero-Shot Classification by Adapting VLMs with Text DescriptionsCode1
Open-Pose 3D Zero-Shot Learning: Benchmark and ChallengesCode1
Lite-Mind: Towards Efficient and Robust Brain Representation NetworkCode1
SCLIP: Rethinking Self-Attention for Dense Vision-Language InferenceCode1
ViT-Lens: Towards Omni-modal RepresentationsCode1
Re-Scoring Using Image-Language Similarity for Few-Shot Object DetectionCode1
ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language ModelsCode1
EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression RecognitionCode1
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object DetectionCode1
CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-FreeCode1
TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual ClassificationCode1
Towards Realistic Zero-Shot Classification via Self Structural Semantic AlignmentCode1
Adversarial Illusions in Multi-Modal EmbeddingsCode1
Image-free Classifier Injection for Zero-Shot ClassificationCode1
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain AdaptationCode1
PerceptionCLIP: Visual Classification by Inferring and Conditioning on ContextsCode1
PRIOR: Prototype Representation Joint Learning from Medical Images and ReportsCode1
MineralImage5k: A benchmark for zero-shot raw mineral visual recognition and descriptionCode1
UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment AnalysisCode1
Improved Probabilistic Image-Text RepresentationsCode1
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language ModelsCode1
Parts of Speech-Grounded Subspaces in Vision-Language ModelsCode1
S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist CaptionsCode1
MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and TextsCode1
The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification TasksCode1
SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)Code1
Exploring Vision-Language Models for Imbalanced LearningCode1
Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor AttacksCode1
Teaching CLIP to Count to TenCode1
Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable DiffusionCode1
CHiLS: Zero-Shot Image Classification with Hierarchical Label SetsCode1
Learning Customized Visual Models with Retrieval-Augmented KnowledgeCode1
Attentive Mask CLIPCode1
Reproducible scaling laws for contrastive language-image learningCode1
LidarCLIP or: How I Learned to Talk to Point CloudsCode1
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive LearningCode1
SuS-X: Training-Free Name-Only Transfer of Vision-Language ModelsCode1
Visual Classification via Description from Large Language ModelsCode1
CALIP: Zero-Shot Enhancement of CLIP with Parameter-free AttentionCode1
Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield NetworksCode1
Show:102550
← PrevPage 2 of 9Next →

No leaderboard results yet.