HugoHE commited on
Commit
a6357ae
·
verified ·
1 Parent(s): ead5489

Update model card to clarify fine-tuning objective: mitigating hallucination on out-of-distribution data

Browse files
Files changed (1) hide show
  1. README.md +7 -5
README.md CHANGED
@@ -9,7 +9,7 @@ tags:
9
  - bdd100k
10
  - autonomous-driving
11
  - BDD 100K
12
- - fine-tuned
13
  pipeline_tag: object-detection
14
  datasets:
15
  - bdd100k
@@ -31,15 +31,15 @@ model-index:
31
  value: "TBD"
32
  ---
33
 
34
- # YOLOv10 - Berkeley DeepDrive (BDD) 100K Fine-tuned
35
 
36
- YOLOv10 model fine-tuned on Berkeley DeepDrive (BDD) 100K dataset for enhanced object detection in autonomous driving scenarios.
37
 
38
  ## Model Details
39
 
40
  - **Model Type**: YOLOv10 Object Detection
41
  - **Dataset**: Berkeley DeepDrive (BDD) 100K
42
- - **Training Method**: fine-tuned
43
  - **Framework**: PyTorch/Ultralytics
44
  - **Task**: Object Detection
45
 
@@ -79,7 +79,9 @@ for result in results:
79
 
80
  ## Model Performance
81
 
82
- This model was fine-tuned on the Berkeley DeepDrive (BDD) 100K dataset using YOLOv10 architecture.
 
 
83
 
84
  ## Intended Use
85
 
 
9
  - bdd100k
10
  - autonomous-driving
11
  - BDD 100K
12
+ - from-scratch
13
  pipeline_tag: object-detection
14
  datasets:
15
  - bdd100k
 
31
  value: "TBD"
32
  ---
33
 
34
+ # YOLOv10 - Berkeley DeepDrive (BDD) 100K Vanilla
35
 
36
+ YOLOv10 model fine-tuned on Berkeley DeepDrive (BDD) 100K dataset to mitigate hallucination on out-of-distribution data in autonomous driving scenarios.
37
 
38
  ## Model Details
39
 
40
  - **Model Type**: YOLOv10 Object Detection
41
  - **Dataset**: Berkeley DeepDrive (BDD) 100K
42
+ - **Training Method**: fine-tuned to mitigate hallucination on out-of-distribution data
43
  - **Framework**: PyTorch/Ultralytics
44
  - **Task**: Object Detection
45
 
 
79
 
80
  ## Model Performance
81
 
82
+ This model was fine-tuned to mitigate hallucination on out-of-distribution data on the Berkeley DeepDrive (BDD) 100K dataset using YOLOv10 architecture.
83
+
84
+ **Fine-tuning Objective**: This model was specifically fine-tuned to mitigate hallucination on out-of-distribution (OOD) data, improving robustness when encountering images that differ from the training distribution.
85
 
86
  ## Intended Use
87