Papers with Code 아카이브

Object Hallucination

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/AikyamLab/hallucinogen

공식 코드

HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models

https://github.com/PKU-YuanGroup/MoE-LLaVA

공식 코드

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

https://github.com/SunJiamei/LRP-imagecaptioning-pytorch

공식 코드

Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models

https://github.com/abzb1/f-clip

공식 코드

Vision-Encoders (Already) Know What They See: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore

https://github.com/aidaslab/second

공식 코드

SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding

https://github.com/anonymousanoy/fohe

공식 코드

Mitigating Fine-Grained Hallucination by Fine-Tuning Large Vision-Language Models with Caption Rewrites

https://github.com/apple/ml-ferret

공식 코드

Ferret: Refer and Ground Anything Anywhere at Any Granularity

https://github.com/billchan226/halc

공식 코드

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

https://github.com/bradyfu/awesome-multimodal-large-language-models

공식 코드

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

https://github.com/bronyayang/HallE_Switch

공식 코드

HallE-Control: Controlling Object Hallucination in Large Multimodal Models

https://github.com/bronyayang/halle_control

공식 코드

HallE-Control: Controlling Object Hallucination in Large Multimodal Models

https://github.com/bscho333/ReVisiT

공식 코드

Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs

https://github.com/d-ailin/clip-guided-decoding

공식 코드

Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding

https://github.com/damo-nlp-sg/vcd

공식 코드

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

https://github.com/feielysia/viecap

공식 코드

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning

https://github.com/furkanbiten/object-bias

공식 코드

Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning

https://github.com/gmum/3d-point-clouds-autocomplete

공식 코드

HyperPocket: Generative Point Cloud Completion

https://github.com/haoyu-bu/CAFe

공식 코드

CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning

https://github.com/hendryx-scale/mhal-detect

공식 코드

Detecting and Preventing Hallucinations in Large Vision Language Models

https://github.com/hyperwjf/logiccheckgpt

공식 코드

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models

https://github.com/jiaqi5598/adavib

공식 코드

Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow

https://github.com/jihoonlee9898/rvcd

공식 코드

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models

https://github.com/jinhaoduan/truthprint

공식 코드

TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention

https://github.com/kuan2jiu99/audio-hallucination

공식 코드

Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models

https://github.com/ltu-machine-learning/idocvqa

공식 코드

Instruction Makes a Difference

https://github.com/naver-ai/clip4dm

공식 코드

Extract Free Dense Misalignment from CLIP

https://github.com/openbmb/omnilmm

공식 코드

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

https://github.com/opengvlab/multi-modality-arena

공식 코드

LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models

https://github.com/rlhf-v/rlaif-v

공식 코드

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

https://github.com/rucaibox/pope

공식 코드

Evaluating Object Hallucination in Large Vision-Language Models

https://github.com/sled-group/moh

공식 코드

Multi-Object Hallucination in Vision-Language Models

https://github.com/starreeze/efuf

공식 코드

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models

https://github.com/ustc-hyin/ClearSight

공식 코드

ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models

https://github.com/wenliangdai/vlp-object-hallucination

공식 코드

Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training

https://github.com/wujunjie1998/tri-he

공식 코드

Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models

https://github.com/xing0047/cca-llava

공식 코드

Mitigating Object Hallucination via Concentric Causal Attention

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.