Skip to content
Avatar
🏠
Working from home
🏠
Working from home

Highlights

  • Pro
Block or Report

Block or report Confusezius

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Add an optional note:
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Confusezius/README.md

Hello there 👋

🌱 Currently:

🌱 Previously:

🤔 Most of my current work focuses on multimodal & contrastive representation learning as well as out-of-distribution generalization, with particular interests in zero- and few-shot learning.

📫 Reach me for collabs or just general questions here.

You can find me on Twitter or LinkedIn - for my research and latest updates, check out my Google Scholar and Homepage!

Repo stats

Pinned

  1. PyTorch Implementation for Deep Metric Learning Pipelines

    Python 533 90

  2. (ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent…

    Python 311 54

  3. Liver Lesion Segmentation with 2D Unets

    Python 83 26

  4. (CVPR 2020) This repo contains code for "PADS: Policy-Adapted Sampling for Visual Similarity Learning", which proposes learnable triplet mining with Reinforcement Learning.

    Python 57 9

  5. (ICCV 2019) This repo contains code for "MIC: Mining Interclass Characteristics for Improved Metric Learning", which proposes an auxiliary training task to explain away intra-class variations.

    Python 57 5

  6. (ICML 2021) Implementation for S2SD - Simultaneous Similarity-based Self-Distillation for Deep Metric Learning. Paper Link: https://arxiv.org/abs/2009.08348

    Python 34 6

166 contributions in the last year

Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Mon Wed Fri

Contribution activity

October 2022

Created 1 commit in 1 repository

Seeing something unexpected? Take a look at the GitHub profile guide.