Back to Home

Assignment 1: Deep Learning Suite

👥 Team Members & Responsibilities

No. Full Name Student ID Task Responsibility
1Vũ Hoàng Tùng2252886Text Classification (RNN vs Transformer)
2Vũ Minh Quân2212828Image Classification (CNN vs ViT)
3Nguyễn Việt Hoàng2252235Multimodal (Zero-shot vs Few-shot)
Task 1: Text Classification

Extreme Multi-Label Text Classification

Applying Label Wise Attention for 2 datasets with extreme label space (>4k labels) and imbalance (including zero-shot): Eurlex-57K and StackExchange.

Task 2: Image Classification

FGVC-Aircraft Classification

Comparing and optimizing CNN (ResNet-50) and ViT (ViT-B/16) architectures on the FGVC-Aircraft dataset.

Task 3: Multimodal Classification

Multimodal Food-101 Classification

Optimizing CLIP for food classification on the Food-101 dataset, comparing zero-shot and few-shot performance, and analyzing failure cases.