Kaan Özaltan comments

Results 4 comments of


                                            Kaan Özaltan

DINOv2 meets text - Zero-shot segmentation reproductibility

@alexcbb @jbdel @baldassarreFe Hello, is there an update on the sample code for open vocabulary segmentation? I am able to reproduce similar results on ADE20K but I am not sure...

Ambiguity in Semantic Segmentation Masks from SAM3's Text-to-Mask Prediction

I was wondering if the code used for evaluating semantic segmentation will be published. With my own code, I am able to get 37.94% mIoU on ADE-150, as opposed to...

Ambiguity in Semantic Segmentation Masks from SAM3's Text-to-Mask Prediction

@cryingdxy I used this function for evaluation: ``` def predict_semantic_map(processor, image, labels): h, w = image.height, image.width num_classes = len(labels) score_maps = np.zeros((num_classes + 1, h, w), dtype=np.float32) state =...

Ambiguity in Semantic Segmentation Masks from SAM3's Text-to-Mask Prediction

@JuiceCoffe I used these values: ``` MASK_SCORE_THRESHOLD = 0.7 MIN_MASK_AREA_PIXELS = 25 ```