Pierre-François DP
@pfdeplaen.bsky.social
Final-year PhD student in computer vision at KU Leuven, Belgium.
Minimizing entropy only to realize my level of surprise increased
gh.io/pf
Minimizing entropy only to realize my level of surprise increased
gh.io/pf
ViT-5.0, way larger but the size is kept private by OpenAI
August 22, 2025 at 3:21 PM
ViT-5.0, way larger but the size is kept private by OpenAI
Some universities give monetary rewards to scientists when they publish, so these researchers may be incentivised to slice a paper to earn more
May 18, 2025 at 9:47 AM
Some universities give monetary rewards to scientists when they publish, so these researchers may be incentivised to slice a paper to earn more
I completely agree! The issue however is that authors can't engage in the discussion unless reviewers respond or ask for a clarification, and that most reviewers don't
April 6, 2025 at 8:59 PM
I completely agree! The issue however is that authors can't engage in the discussion unless reviewers respond or ask for a clarification, and that most reviewers don't
It's stated that "the reviewer is required to acknowledge the response and agree to update the review in light of the response if necessary"
April 6, 2025 at 8:55 PM
It's stated that "the reviewer is required to acknowledge the response and agree to update the review in light of the response if necessary"
Yes, the discussion is until April 8th. Still, reviewers had to acknowledge and update reviews by April 4th at last
April 6, 2025 at 11:15 AM
Yes, the discussion is until April 8th. Still, reviewers had to acknowledge and update reviews by April 4th at last
We're still waiting to hear back from the conference, but I have little expectations at this stage...
March 24, 2025 at 5:05 PM
We're still waiting to hear back from the conference, but I have little expectations at this stage...
It is unfortunately not even discussed so far... I'm in favour of the motion !
March 11, 2025 at 9:37 AM
It is unfortunately not even discussed so far... I'm in favour of the motion !
Ok, thank you for the answer!
March 3, 2025 at 3:00 PM
Ok, thank you for the answer!
Are there plans to organize a CVPR conference outside of North America?
March 3, 2025 at 2:44 PM
Are there plans to organize a CVPR conference outside of North America?
4/n
We investigate various applications:
- extending the PCA algorithm to non-linear decorrelation
- learning minimally redundant representations for SSL
- learning features that generalize beyond label supervision in supervised learning
We investigate various applications:
- extending the PCA algorithm to non-linear decorrelation
- learning minimally redundant representations for SSL
- learning features that generalize beyond label supervision in supervised learning
February 21, 2025 at 11:19 AM
4/n
We investigate various applications:
- extending the PCA algorithm to non-linear decorrelation
- learning minimally redundant representations for SSL
- learning features that generalize beyond label supervision in supervised learning
We investigate various applications:
- extending the PCA algorithm to non-linear decorrelation
- learning minimally redundant representations for SSL
- learning features that generalize beyond label supervision in supervised learning
3/n
Our method employs an adversarial game where small networks identify dependencies among feature dimensions, while the main network exploits this information to reduce dependencies.
Our method employs an adversarial game where small networks identify dependencies among feature dimensions, while the main network exploits this information to reduce dependencies.
February 21, 2025 at 11:17 AM
3/n
Our method employs an adversarial game where small networks identify dependencies among feature dimensions, while the main network exploits this information to reduce dependencies.
Our method employs an adversarial game where small networks identify dependencies among feature dimensions, while the main network exploits this information to reduce dependencies.
2/n
Currently, most ML techniques rely on minimizing the covariance between output feature dimensions to extract minimally redundant representations.
Still, this is not sufficient as linearly uncorrelated variables can still exhibit nonlinear relationships.
Currently, most ML techniques rely on minimizing the covariance between output feature dimensions to extract minimally redundant representations.
Still, this is not sufficient as linearly uncorrelated variables can still exhibit nonlinear relationships.
![Example of uncorrelated random variables that are not independent: x_2 = (x_1)^2 with x_1 uniformly distributed on [-1,1]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:5nylgvokyyqesolnwui2efzk/bafkreifcipe2w4b6cpvsvi2hysohy47pdksullwqscjmcwwxyjswytznca@jpeg)
February 21, 2025 at 11:16 AM
2/n
Currently, most ML techniques rely on minimizing the covariance between output feature dimensions to extract minimally redundant representations.
Still, this is not sufficient as linearly uncorrelated variables can still exhibit nonlinear relationships.
Currently, most ML techniques rely on minimizing the covariance between output feature dimensions to extract minimally redundant representations.
Still, this is not sufficient as linearly uncorrelated variables can still exhibit nonlinear relationships.
I miss the video explanation 🎶
February 14, 2025 at 7:24 PM
I miss the video explanation 🎶
Reinforcement learning: read the "popular with friends" feed and follow new accounts.
January 12, 2025 at 6:36 PM
Reinforcement learning: read the "popular with friends" feed and follow new accounts.
As a reviewer, it's difficult to check for potential plagiarism (eg from an arXiv preprint) as we don't have access to the authors' names and should avoid breaking anonymity.
Should conferences implement a new "role" dedicated to spot plagiarism?
@cvprconference.bsky.social @iclr-conf.bsky.social
Should conferences implement a new "role" dedicated to spot plagiarism?
@cvprconference.bsky.social @iclr-conf.bsky.social
January 10, 2025 at 11:59 AM
As a reviewer, it's difficult to check for potential plagiarism (eg from an arXiv preprint) as we don't have access to the authors' names and should avoid breaking anonymity.
Should conferences implement a new "role" dedicated to spot plagiarism?
@cvprconference.bsky.social @iclr-conf.bsky.social
Should conferences implement a new "role" dedicated to spot plagiarism?
@cvprconference.bsky.social @iclr-conf.bsky.social
The only real new contribution in our opinion is an evaluation in combination with newer variants of DETR. It's highly unlikely the paper would have been accepted if the reviewers were aware of our earlier work.
January 10, 2025 at 11:57 AM
The only real new contribution in our opinion is an evaluation in combination with newer variants of DETR. It's highly unlikely the paper would have been accepted if the reviewers were aware of our earlier work.
Looking closer into the paper, it becomes obvious that the claimed contributions are all rephrasings of ours. For any of the remaining (minor) differences, the two methods are not explicitly compared in the paper, neither experimentally nor in the discussion, although that's what one would expect...
January 10, 2025 at 11:57 AM
Looking closer into the paper, it becomes obvious that the claimed contributions are all rephrasings of ours. For any of the remaining (minor) differences, the two methods are not explicitly compared in the paper, neither experimentally nor in the discussion, although that's what one would expect...
Deliberately concealing the similarities between the two works and reusing our illustrations without properly quoting are clear scientific integrity violations that require to be addressed. We reported the case to the PCs and hope the conference will take proper action.
January 10, 2025 at 11:57 AM
Deliberately concealing the similarities between the two works and reusing our illustrations without properly quoting are clear scientific integrity violations that require to be addressed. We reported the case to the PCs and hope the conference will take proper action.
Our CVPR 2023 paper: arxiv.org/pdf/2307.02402
The ACMMM'24 paper's open review: openreview.net/forum?id=N3y...
The ACMMM'24 paper's open review: openreview.net/forum?id=N3y...
arxiv.org
January 10, 2025 at 11:53 AM
Our CVPR 2023 paper: arxiv.org/pdf/2307.02402
The ACMMM'24 paper's open review: openreview.net/forum?id=N3y...
The ACMMM'24 paper's open review: openreview.net/forum?id=N3y...