ZuchniakK / MTKDLinks
Multi-Teacher Knowledge Distillation, code for my PhD dissertation. I used knowledge distillation as a decision-fusion and compressing mechanism for ensemble models.
☆20Updated 2 years ago
Alternatives and similar repositories for MTKD
Users that are interested in MTKD are comparing it to the libraries listed below
Sorting:
- This is the implementation for the ICME-2023 paper (Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning).☆26Updated 2 years ago
- Code for "Dual Focal Loss for Calibration" (ICML 2023)☆32Updated 2 months ago
- ☆26Updated last year
- Training ImageNet / CIFAR models with sota strategies and fancy techniques such as ViT, KD, Rep, etc.☆82Updated last year
- Official implementation for "Knowledge Distillation with Refined Logits".☆14Updated 10 months ago
- This is the official code for paper: Token Summarisation for Efficient Vision Transformers via Graph-based Token Propagation☆29Updated last year
- Wavelet-Attention CNN for Image Classification☆29Updated 3 years ago
- [NeurIPS2023]Lightweight Vision Transformer with Bidirectional Interaction☆24Updated last year
- pytorch implements data enhancement and network regularization methods: cutmix, cutout, shakedrop, mixup, Label smoothing☆10Updated 3 years ago
- AMTML-KD: Adaptive Multi-teacher Multi-level Knowledge Distillation☆59Updated 4 years ago
- [ICML 2022] This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). We suggest to use an L…☆11Updated 2 years ago
- This repository periodicly updates the MTL paper and resources☆56Updated 2 months ago
- This resposity maintains a collection of important papers on knowledge distillation (awesome-knowledge-distillation)).☆78Updated 3 months ago
- Create reliability diagrams to quantify ML calibration.☆10Updated 3 years ago
- Learning with Noisy Labels, Label Noise, ICML 2021☆45Updated 2 years ago
- Trainable Highly-expressive Activation Functions. ECCV 2024☆38Updated 4 months ago
- Official implementation of paper "Knowledge Distillation from A Stronger Teacher", NeurIPS 2022☆146Updated 2 years ago
- Implementation of AAAI 2022 Paper: Go wider instead of deeper☆32Updated 2 years ago
- ☆76Updated last year
- PolyLoss implementation using PyTorch☆12Updated 3 years ago
- ☆47Updated 2 years ago
- Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation. NeurIPS 2022.☆32Updated 2 years ago
- AdaTask: A Task-Aware Adaptive Learning Rate Approach to Multi-Task Learning. AAAI, 2023.☆28Updated last year
- ☆11Updated last year
- ☆10Updated last year
- [ICANN 2022 Oral] This repository includes the official project of TFCNs, presented in our paper: TFCNs: A CNN-Transformer Hybrid Networ…☆17Updated 2 years ago
- ☆23Updated last year
- Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction☆11Updated 3 years ago
- Polyloss Pytorch Implementation☆44Updated 3 years ago
- Pytorch implementation (TPAMI 2023) - Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion☆19Updated 2 years ago