Update app.py

app.py

@@ -33,6 +33,66 @@ model = GenerativeInferenceModel()
 
 # Define example images and their parameters with updated values from the research
 examples = [
+    {
+        "image": os.path.join("stimuli", "farm1.jpg"),
+        "name": "farm1",
+        "wiki": "https://en.wikipedia.org/wiki/Visual_perception",
+        "papers": [
+            "[Adversarially Robust Vision](https://github.com/MadryLab/robustness)",
+            "[Generative Inference](https://doi.org/10.1016/j.tics.2003.08.003)"
+        ],
+        "method": "Prior-Guided Drift Diffusion",
+        "reverse_diff": {
+            "model": "resnet50_robust",
+            "layer": "all",
+            "initial_noise": 0.0,
+            "diffusion_noise": 0.02,
+            "step_size": 1.0,
+            "iterations": 501,
+            "epsilon": 40.0
+        },
+        "inference_normalization": "off",
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 0.3,
+        "eps_max_mult": 300.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 10.0,
+        "step_min_mult": 1.0,
+    },
+    {
+        "image": os.path.join("stimuli", "ArtGallery1.jpg"),
+        "name": "ArtGallery1",
+        "wiki": "https://en.wikipedia.org/wiki/Visual_perception",
+        "papers": [
+            "[Adversarially Robust Vision](https://github.com/MadryLab/robustness)",
+            "[Generative Inference](https://doi.org/10.1016/j.tics.2003.08.003)"
+        ],
+        "method": "Prior-Guided Drift Diffusion",
+        "reverse_diff": {
+            "model": "resnet50_robust",
+            "layer": "layer4",
+            "initial_noise": 0.5,
+            "diffusion_noise": 0.002,
+            "step_size": 0.1,
+            "iterations": 501,
+            "epsilon": 40.0
+        },
+        "inference_normalization": "off",
+        "use_adaptive_eps": False,
+        "use_adaptive_step": True,
+        "mask_center_x": 0.0,
+        "mask_center_y": -1.0,
+        "mask_radius": 0.1,
+        "mask_sigma": 0.2,
+        "eps_max_mult": 30.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 100.0,
+        "step_min_mult": 1.0,
+    },
     {
         "image": os.path.join("stimuli", "urbanoffice1.jpg"),
         "name": "UrbanOffice1",
@@ -80,7 +140,17 @@ examples = [
             "step_size": 1.0,
             "iterations": 101,
             "epsilon": 20.0
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "Kanizsa_square.jpg"),
@@ -99,7 +169,17 @@ examples = [
             "step_size": 0.64,
             "iterations": 100,
             "epsilon": 5.0
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "CornsweetBlock.png"),
@@ -119,7 +199,17 @@ examples = [
             "step_size": 0.8,
             "iterations": 51,
             "epsilon": 20.0
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "face_vase.png"),
@@ -138,7 +228,17 @@ examples = [
             "step_size": 0.58,
             "iterations": 100,
             "epsilon": 0.81
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "Confetti_illusion.png"),
@@ -157,7 +257,17 @@ examples = [
             "step_size": 0.5,
             "iterations": 101,
             "epsilon": 20.0
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "EhresteinSingleColor.png"),
@@ -176,7 +286,17 @@ examples = [
             "step_size": 0.8,
             "iterations": 101,
             "epsilon": 20.0
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "GroupingByContinuity.png"),
@@ -195,7 +315,17 @@ examples = [
             "step_size": 0.4,
             "iterations": 101,
             "epsilon": 4.0
-        }
+        },
+        "use_adaptive_eps": False,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
+        "mask_center_y": 0.0,
+        "mask_radius": 0.2,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
+        "eps_min_mult": 1.0,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     },
     {
         "image": os.path.join("stimuli", "figure_ground.png"),
@@ -214,37 +344,17 @@ examples = [
             "step_size": 0.5,
             "iterations": 101,
             "epsilon": 3.0
-        }
-    },
-    {
-        "image": os.path.join("stimuli", "urbanoffice1.jpg"),
-        "name": "UrbanOffice1",
-        "wiki": "https://en.wikipedia.org/wiki/Visual_perception",
-        "papers": [
-            "[Adversarially Robust Vision](https://github.com/MadryLab/robustness)",
-            "[Generative Inference](https://doi.org/10.1016/j.tics.2003.08.003)"
-        ],
-        "method": "Prior-Guided Drift Diffusion",
-        "reverse_diff": {
-            "model": "resnet50_robust",
-            "layer": "all",
-            "initial_noise": 1.0,
-            "diffusion_noise": 0.002,
-            "step_size": 1.0,
-            "iterations": 500,
-            "epsilon": 40.0
         },
-        "inference_normalization": "off",
         "use_adaptive_eps": False,
-        "use_adaptive_step": True,
-        "mask_center_x": 0.5,
+        "use_adaptive_step": False,
+        "mask_center_x": 0.0,
         "mask_center_y": 0.0,
         "mask_radius": 0.2,
-        "mask_sigma": 0.2,
-        "eps_max_mult": 20.0,
+        "mask_sigma": 1.0,
+        "eps_max_mult": 1.0,
         "eps_min_mult": 1.0,
-        "step_max_mult": 50.0,
-        "step_min_mult": 0.2,
+        "step_max_mult": 1.0,
+        "step_min_mult": 1.0,
     }
 ]
 
@@ -398,6 +508,10 @@ def draw_mask_overlay(image, center_x, center_y, radius):
 # Helper function to apply example parameters (adaptive mask off by default unless example defines it)
 def apply_example(example):
     rd = example["reverse_diff"]
+    mcx = example.get("mask_center_x", 0.0)
+    mcy = example.get("mask_center_y", 0.0)
+    mrad = example.get("mask_radius", 0.3)
+    mask_img = draw_mask_overlay(example["image"], mcx, mcy, mrad)
     return [
         example["image"],
         rd.get("model", "resnet50_robust"),
@@ -410,14 +524,15 @@ def apply_example(example):
         rd["layer"],
         example.get("use_adaptive_eps", False),
         example.get("use_adaptive_step", False),
-        example.get("mask_center_x", 0.0),
-        example.get("mask_center_y", 0.0),
+        mcx,
+        mcy,
         example.get("mask_radius", 0.3),
         example.get("mask_sigma", 0.2),
         example.get("eps_max_mult", 4.0),
         example.get("eps_min_mult", 1.0),
         example.get("step_max_mult", 4.0),
         example.get("step_min_mult", 1.0),
+        mask_img,
         gr.Group(visible=True),
     ]
 
@@ -501,7 +616,7 @@ with gr.Blocks(title="Human Hallucination Prediction", css="""
                     mask_center_y_slider = gr.Slider(minimum=-1.0, maximum=1.0, value=0.0, step=0.05, label="Mask center Y")
                 with gr.Row():
                     mask_radius_slider = gr.Slider(minimum=0.01, maximum=1.0, value=0.2, step=0.01, label="Mask radius (flat region size)")
-                    mask_sigma_slider = gr.Slider(minimum=0.05, maximum=0.5, value=0.2, step=0.01, label="Mask sigma (fall-off outside radius)")
+                    mask_sigma_slider = gr.Slider(minimum=0.05, maximum=1.0, value=0.2, step=0.01, label="Mask sigma (fall-off outside radius)")
                 with gr.Row():
                     eps_max_mult_slider = gr.Slider(minimum=0.1, maximum=350.0, value=20.0, step=0.1, label="Epsilon: multiplier at center")
                     eps_min_mult_slider = gr.Slider(minimum=0.1, maximum=10.0, value=1.0, step=0.1, label="Epsilon: multiplier at periphery")
@@ -540,6 +655,7 @@ with gr.Blocks(title="Human Hallucination Prediction", css="""
                         mask_radius_slider, mask_sigma_slider,
                         eps_max_mult_slider, eps_min_mult_slider,
                         step_max_mult_slider, step_min_mult_slider,
+                        mask_preview,
                         params_section,
                     ],
                 )