Comments (9)
Wow, the results seem very inspiring if there's no bug.
I haven't tried such a memory-based clustering baseline. I did not try to re-extract the features and re-init the memory for each epoch in the experiments regarding this paper. I have only tried to re-extract the features and re-init the classifier for conventional clustering-based baselines without memory.
Anyway, if all the steps are right without any potential bugs, it's quite a super-strong baseline for unsupervised re-ID. And the memory seems to help a lot!
from spcl.
Plus, I am curious about the results of such a baseline if outliers are used for training.
from spcl.
Since the oracle experiment (same training pipeline but with ground-truth identities instead) on the unsupervised Market-1501 only achieves 82.3% mAP. So one important thing that needs to be double-checked first is that you did not wrongly consider the ground-truth identities as pseudo identities for training.
from spcl.
Ok, i'll double-check my code. In the meantime, can you try running a baseline experiment like the one I described? Maybe when you have time?
from spcl.
Sure. I will also try it when I am free. Keep in touch if any updates.
from spcl.
Hi, i re-run the experiment using an altered dataset, where the first 4 digits of image names are random shuffled (e.g. '0067_c1s1_009376_01.jpg'-->'3456_c1s1_009376_01.jpg'), and the performance is the same. I'll make further check to be sure, but if the result is correct, i think it comes from two aspects:
- Re-constructing and re-initializing memory bank as non-parametric classifiers is indeed helpful for unsupervised re-ID (why?);
- The RandomMultiGallerySampler that you used to sample data helps balance the sampling under different cameras, which is beneficial; (i'll do an ablation on this sampling part later)
Have you got any updates and understanding on the baseline?
from spcl.
My experiment is still in the process, but I guess it will achieve similar results as you mentioned. Regarding your questions:
- Yes. I have also found that using memory as a non-parametric classifier and training with such a memory-based contrastive loss could perform better than a sole cross-entropy loss in fully-supervised tasks (I tested on MSMT17 and Market-1501), where I only constructed and initialized the memory once at the beginning and I am not sure whether further improvements can be achieved by re-constructing and re-initializing before each epoch. I did not try to combine with other metrics (e.g. triplet loss, circle loss, etc.), so I am not sure whether memory-based loss could still outperform cross-entropy loss when combining with other metrics. I am interested in it. I guess the gains come from the class(cluster)-wise momentum update strategy, which is expected to be slower than conventional optimization. But I am still confused about why slower updates could help so much, either in supervised or in unsupervised setups. It's quite an interesting and open question and I am looking forward to your further studies! I think it would become an inspiring empirical paper (I even got the title "In defense of the memory-based classifier for person re-identification", haha, I am just joking). I recommend to test it on more tasks and more datasets, e.g. supervised, unsupervised domain adaptation, unsupervised. And then we can know if such a super-strong baseline works under various conditions. I have no idea how to explain the effects of it theoretically now. We can think about it further.
- Yes. Another issue regarding this sampler (open-mmlab/OpenUnReID#20) mentioned that it seems to perform better than the previous identity-based sampler. I did not do an ablation study on it and look forward to your results.
Plus, with this baseline, I am wondering whether training with outliers would still work.
from spcl.
I finished the training and achieved 78.3% mAP and 90.7% top-1. Got confirmed!
from spcl.
Great! I send you an email ([email protected]) so that we can discuss further.
from spcl.
Related Issues (20)
- TypeError: in method 'bruteForceKnn', argument 12 of type 'faiss::Index::idx_t *' HOT 1
- number of instances in each mini batch HOT 1
- `fassi-gpu` version should be fixed below `v1.6.4` HOT 2
- Question about the paper HOT 2
- low result with only 1 GPU HOT 1
- Question on PersonX HOT 1
- Performance on MSMT17 HOT 2
- How to train/test on the source domain
- VehicleX Datasets HOT 3
- [CUDA 11.2] Experiment on RTX 3090 with faiss-gpu 1.6.5
- problem with rerank
- There are some questions related to the cluster center in the code HOT 1
- hello, anyone meet this error? HOT 8
- 聚类紧密度计算 HOT 1
- PermissionError: [Errno 1] Operation not permitted HOT 2
- indep_thres is defined by the top-90%?why? HOT 2
- Is there anybody meet this problem?
- Memory Error
- About NMI scores
- About the momentum update
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from spcl.