wl-zhao/DIML
[ICCV 2021] Towards Interpretable Deep Metric Learning with Structural Matching
This project helps computer vision researchers or machine learning engineers understand why their models perceive two images as similar or different. It takes two images and outputs not just a similarity score, but also highlights which specific parts or features in each image contribute most to that score. Researchers working on image retrieval, face recognition, or product recommendations would find this useful.
102 stars. No commits in the last 6 months.
Use this if you need to debug or explain the decision-making process of your deep metric learning models for image similarity.
Not ideal if you are looking for an out-of-the-box solution for general image classification or object detection tasks.
Stars
102
Forks
12
Language
Python
License
—
Category
Last pushed
Aug 13, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wl-zhao/DIML"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)