---
title: Illumination-Invariant Fish Classification
emoji: 🐟
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: "6.5.1"
python_version: "3.10"
app_file: app.py
pinned: false
---

# Illumination-Invariant Identification of Wild and Farmed Larimichthys crocea

via Cross-Modal 3D Shape Priors

## Overview

This Space demonstrates an illumination-invariant fish classification system that identifies wild and farmed Larimichthys crocea (yellow croaker) using cross-modal 3D shape priors.

## Features

- **Multi-modal Fusion**: Integrates RGB and depth information for enhanced feature representation
- **Shape-Guided Attention**: Leverages depth-estimated shape information to guide RGB feature learning
- **Real-time Inference**: Fast classification with pre-trained models
- **Grad-CAM Visualization**: Visualize model attention with heatmaps

## Usage

Upload an image of a fish, and the system will:
1. Detect if it's a yellow croaker (confidence threshold: 0.5)
2. If detected, classify it as Wild or Farmed
3. Display detection mask and Grad-CAM heatmap for interpretability

## Model Architecture

- **Backbone**: ResNet50
- **Depth Decoder**: UNet-style decoder with attention gates
- **Classification Head**: Fully connected layers with dropout

## Citation

If you use this code in your research, please cite: