Cv Multitask Pipeline

--- license: mit tags: - computer-vision - object-detection - image-classification - multi-task-learning - pytorch - efficientnet datasets: - pascal-voc-2012 --- # CV Multitask Pipeline Multi-task computer vision model performing simultaneous object classification and bounding box detection on PASCAL VOC 2012 (20 classes). ## Model Details - **Architecture:** Frozen EfficientNet-B0 backbone + custom classification head + custom detection head - **Backbone:** ImageNet-pretrained EfficientNet-B0 (frozen, 4M params) - **Classification head:** 667K trainable params, outputs 20-class logits - **Detection head:** 329K trainable params, outputs normalized bbox coordinates ## Training - **Dataset:** PASCAL VOC 2012 (5,717 train / 5,823 val images) - **Epochs:** 30 (best checkpoint at epoch 5) - **Loss:** Weighted multi-task loss (CrossEntropy + SmoothL1, λ_cls=1.0, λ_det=5.0) - **Hardware:** Google Colab T4 GPU ## Results | Metric | Value | |--------|-------| | Top-1 Accuracy | 79.9% | | Mean IoU | 0.468 | | [email protected] Accuracy | 49.2% | ## Usage ```python import torch from huggingface_hub import hf_hub_download checkpoint_path = hf_hub_download( repo_id="OmUniyal/cv-multitask-pipeline", filename="best_model.pt" ) checkpoint = torch.load(checkpoint_path, map_location="cpu", weights_only=True) ``` Full model code and inference pipeline: [GitHub repo](https://github.com/OmUniyal/cv-multitask-pipeline) ## Limitations - Closed-set classification — no "none of the above" option for out-of-distribution images - Overfitting observed after epoch 5 - Single bbox regression — doesn't handle multiple objects per image ## Live Demo [HuggingFace Spaces](https://huggingface.co/spaces/OmUniyal/cv-multitask-pipeline)

Source context: 0 downloads · 0 likes · Pipeline image-classification · Repo omUniyal/cv-multitask-pipeline