Editing Few Shot Zero Shot (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''CLIP zero-shot classification:'''
<syntaxhighlight lang="python">
import torch
import clip
from PIL import Image

model, preprocess = clip.load("ViT-B/32", device="cuda")

# Zero-shot classification without any task-specific training
def zero_shot_classify(image_path: str, class_names: list) -> dict:
    image = preprocess(Image.open(image_path)).unsqueeze(0).to("cuda")
    # Create text descriptions for each class
    texts = clip.tokenize([f"a photo of a {cls}" for cls in class_names]).to("cuda")
    with torch.no_grad():
        image_features = model.encode_image(image)
        text_features = model.encode_text(texts)
        # Normalize and compute cosine similarity
        image_features /= image_features.norm(dim=-1, keepdim=True)
        text_features /= text_features.norm(dim=-1, keepdim=True)
        similarity = (100.0 * image_features @ text_features.T).softmax(dim=-1)
    return {cls: float(sim) for cls, sim in zip(class_names, similarity[0])}

# Works for ANY class names — zero training examples needed!
results = zero_shot_classify("wildlife_photo.jpg",
    ["lion", "elephant", "giraffe", "zebra", "cheetah", "rhinoceros"])
print(sorted(results.items(), key=lambda x: -x[1]))
</syntaxhighlight>

'''Few-shot classification with Prototypical Networks:'''
<syntaxhighlight lang="python">
import torch
import torch.nn.functional as F

def prototypical_classify(support_embeddings, support_labels, query_embeddings, n_classes):
    """
    support_embeddings: (n_classes * k_shot, D) support set embeddings
    query_embeddings: (n_query, D) query embeddings
    Returns: predicted class for each query
    """
    # Compute class prototypes (mean of support embeddings per class)
    prototypes = torch.stack([
        support_embeddings[support_labels == c].mean(0) for c in range(n_classes)
    ])  # (n_classes, D)
    # Classify queries by nearest prototype
    dists = torch.cdist(query_embeddings, prototypes)  # (n_query, n_classes)
    return dists.argmin(dim=1)
</syntaxhighlight>

; Few-shot / zero-shot approach selection
: '''Vision, zero-shot''' → CLIP (ViT-L/14 for best quality)
: '''NLP, zero-shot''' → LLM with task description in system prompt
: '''NLP, few-shot''' → LLM with 3-10 examples in context
: '''Vision, few-shot''' → Fine-tune CLIP or DINO with support set
: '''Structured few-shot''' → Prototypical Networks for consistent task structure
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">