VCD
Object detection method
An approach to reduce object hallucinations in large vision-language models by contrasting output distributions derived from original and distorted visual inputs
[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
222 stars
7 watching
11 forks
Language: Python
last commit: 5 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 szq0214/dsod | A deep learning-based object detection system from scratch | 706 |
 lartpang/ovcamo | Develops an object segmentation algorithm to detect camouflaged objects in images with varying backgrounds and contexts. | 20 |
 yfzhang114/llava-align | Debiasing techniques to minimize hallucinations in large visual language models | 75 |
 yuhangzang/contextdet | An approach to detecting objects in images using multimodal large language models and contextual information | 208 |
 bcdnlp/faithscore | Evaluates answers generated by large vision-language models to assess hallucinations | 27 |
 rucaibox/pope | An evaluation framework for detecting object hallucinations in vision-language models | 187 |
 junyangwang0410/haelm | A framework for detecting hallucinations in large language models | 17 |
 yangxuntu/vrd | This repository provides a framework for visual relationship detection using deep learning models and pre-processing tools. | 94 |
 shengcao-cao/hassod | Develops a neural network architecture for object detection and instance segmentation without labeled data | 52 |
 chenyuntc/dsod.pytorch | An implementation of the Deep Supervised Object Detector from scratch using PyTorch. | 70 |
 jingzhang617/cod-rank-localize-and-segment | Develops a system to detect, segment, and rank camouflaged objects in images. | 74 |
 yiyangzhou/lure | Analyzing and mitigating object hallucination in large vision-language models to improve their accuracy and reliability. | 136 |
 ethanhe42/softer-nms | An object detection technique using bounding box regression and uncertainty estimation to improve accurate detection results | 367 |
 1zhou-wang/memvr | An implementation of a method to mitigate hallucinations in large language models using visual re-tracing | 28 |
 ibm/max-object-detector | A tool for detecting objects in images using deep learning models | 290 |