Bill Psomas

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by...

7/7 Resources 📄

Paper: arxiv.org/abs/2602.23339
Code: github.com/TilemahosAra...

Joint work with: @tim-arav.bsky.social, @stojnicv.xyz, Nikos Komodakis, and @gtolias.bsky.social.

We thank @noagarciad.bsky.social, @skamalas.bsky.social, @ekazakos.bsky.social for the feedback.

See you @ #CVPR2026

6/n 𝑷𝒆𝒓𝒔𝒐𝒏𝒂𝒍𝒊𝒛𝒆𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏

🥤 𝑹𝑵𝑺 can easily be employed for fine-grained tasks like 𝒑𝒆𝒓𝒔𝒐𝒏𝒂𝒍𝒊𝒛𝒆𝒅 𝒔𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏 by simply expanding the support set with a few examples of a specific instance, letting it 𝒔𝒆𝒑𝒂𝒓𝒂𝒕𝒆 𝒕𝒉𝒂𝒕 𝒊𝒏𝒔𝒕𝒂𝒏𝒄𝒆 𝒇𝒓𝒐𝒎 𝒊𝒕𝒔 𝒃𝒓𝒐𝒂𝒅𝒆𝒓 𝒄𝒍𝒂𝒔𝒔.

5/n 𝑩𝒓𝒊𝒅𝒈𝒊𝒏𝒈 𝒕𝒉𝒆 𝑮𝒂𝒑

⚡ 𝑹𝑵𝑺 improves over different kinds of OVS approaches 𝒃𝒚 14.1% 𝒐𝒏 𝒂𝒗𝒆𝒓𝒂𝒈𝒆, while maintaining open-vocabulary generalization.

4/n 𝑫𝒚𝒏𝒂𝒎𝒊𝒄 𝑭𝒆𝒘-𝒔𝒉𝒐𝒕 𝑺𝒄𝒆𝒏𝒂𝒓𝒊𝒐𝒔

We investigate multiple 𝒇𝒆𝒘-𝒔𝒉𝒐𝒕 settings where visual or textual information may be missing for some test classes.

🎉 We consistently improve respective baselines, making 𝑹𝑵𝑺 a 𝒑𝒓𝒂𝒄𝒕𝒊𝒄𝒂𝒍 and 𝒐𝒑𝒆𝒏-𝒘𝒐𝒓𝒍𝒅 𝑶𝑽𝑺 method.

3/n 𝑯𝒐𝒘 it works?

💾 𝑹𝑵𝑺 stores 𝑽𝑳𝑴 𝒇𝒆𝒂𝒕𝒖𝒓𝒆𝒔 from visual and textual examples in a 𝒎𝒆𝒎𝒐𝒓𝒚-𝒆𝒇𝒇𝒊𝒄𝒊𝒆𝒏𝒕 manner.

🖼️ At test time, it 𝒓𝒆𝒕𝒓𝒊𝒆𝒗𝒆𝒔 𝒕𝒆𝒔𝒕 𝒊𝒎𝒂𝒈𝒆 𝒓𝒆𝒍𝒆𝒗𝒂𝒏𝒕 𝒆𝒙𝒂𝒎𝒑𝒍𝒆𝒔 to train a linear classifier on both modalities.

2/n Zero-shot open-vocabulary segmentation (OVS) is significantly underperforming fully supervised.

🌉 𝑹𝑵𝑺 𝒃𝒓𝒊𝒅𝒈𝒆𝒔 𝒕𝒉𝒊𝒔 𝒈𝒂𝒑 using a few pixel-level annotated visual examples along with class names.

With a few adaptation steps on each test image, we improve zero-shot 𝒃𝒚 up to 34% on average.

1/n #CVPR2026 Accepted Paper🚀

𝑨𝒓𝒆 𝒂 𝑭𝒆𝒘 𝑬𝒙𝒂𝒎𝒑𝒍𝒆𝒔 𝑬𝒏𝒐𝒖𝒈𝒉 𝒕𝒐 𝑩𝒓𝒊𝒅𝒈𝒆 𝒕𝒉𝒆 𝑺𝒖𝒑𝒆𝒓𝒗𝒊𝒔𝒊𝒐𝒏 𝑮𝒂𝒑 𝒊𝒏 𝑶𝒑𝒆𝒏-𝑽𝒐𝒄𝒂𝒃𝒖𝒍𝒂𝒓𝒚 𝑺𝒆𝒈𝒎𝒆𝒏𝒕𝒂𝒕𝒊𝒐𝒏?

𝑹𝒆𝒕𝒓𝒊𝒆𝒗𝒆 𝒂𝒏𝒅 𝑺𝒆𝒈𝒎𝒆𝒏𝒕 (𝑹𝑵𝑺) answers this question.

Paper/code at the end👇🏼

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

Tilemachos Aravanis @stojnicv.xyz @billpsomas.bsky.social Nikos Komodakis @gtolias.bsky.social

tl;dr: almost yes if use 1-3 images, no if more(fig 6)
arxiv.org/abs/2602.23339
#CVPR2026

🎉🎉🎉

Excited to share that our paper "Global-Aware Edge Prioritization for Pose Graph Initialization" has been accepted to CVPR 2026! #CVPR2026 See you soon in Denver!🥳🥳 Code is coming soon🚧
❓How would you do an accurate and efficient pose graph initialization in a global manner? arxiv.org/abs/2602.21963

Global-Aware Edge Prioritization for Pose Graph Initialization

@weitong8591.bsky.social, @gtolias.bsky.social, Jiri Matas, @danielbarath.bsky.social

tl;dr: rank pose graph edges->global consistency->improve SfM

arxiv.org/abs/2602.21963

Sleeping while waiting on an “anywhere in the world” paper decision release. #CVPR2026

Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol. However, standard linear probing can understate the capability of models whose pre-training optim...

8/8 Resources 📄

Paper: arxiv.org/abs/2506.10178
Code: github.com/billpsomas/e...

Joint work with: Dionysis Christopoulos,@eirinibaltzi.bsky.social,@ikakogeorgiou.bsky.social, @tim-arav.bsky.social,Nikos Komodakis,Konstantinos Karantzalos,Yannis Avrithis,@gtolias.bsky.social.

See you @ ICLR 2026🇧🇷

7/n Take-home messages 💡

EP:
- Plug-and-play.
- Compatible with all pre-training families.
- Unlocks the potential of encoders optimized for local representations.
- Complementary with PEFT.
- Better to have it, than not to have it. 👀

6/n EP + PEFT = 🔥

- EP captures information that LoRA alone does not, and vice versa.
- LoRA+EP improves over both pure EP and pure LoRA.

📌 Example: a LoRA+EP configuration with 250K params reaches 72%, 4.3% above linear probing (67.7%), while using over 3× fewer parameters.

5/n Interpretability 🔍

- EP queries specialize in distinct spatial regions.
- Attention maps are complementary.
- Semantic correspondences emerge (e.g. tails, feet).
- Verified quantitatively too.

4/n Designed for local representations🧩

📊 Across ImageNet-1K:

- Consistent gains over k-NN and Linear Probing (LP).
- Particularly strong improvements for MIM, VL, and generative.
- Minimal overhead.

3/n Core observation ⚙️

Prior attentive probing uses redundant projections.

🔍 Introducing Efficient Probing (EP):

📌 Multi-query cross-attention.
🔌 Plug-and-play on top of frozen encoders.
💸 Lightweight and parameter-efficient.

2/n Why revisit probing? 🤔

- Linear probing underestimates encoders optimizing local representations.
- Full fine-tuning is costly at scale.
- Attentive probing helps, yet methods are over-parametrized and not well-studied.

👉 Can we get attention benefits without that much overhead?

1/n Attention, Please! 🚀

Our work “Revisiting Attentive Probing Through the Lens of Efficiency” has been accepted at #ICLR2026.

We introduce Efficient Probing (EP) — a lightweight, multi-query attentive probing method for frozen encoders.

Paper + code at the end 👇

BBoxMaskPose v2: Expanding Mutual Conditioning to 3D

Miroslav Purkrabek, Constantin Kolomiiets, Jiri Matas

tl;dr: sota in human pose estimations, especially for the hard cases
arxiv.org/abs/2601.15200

Would love to try

Best promo anyone could make for this position 👏🏾🏰 And, amazingly, everything said is true 🎆

Postdoctoral research position in Instance-level visual generation Czech Technical University in Prague (CTU) offers a fellowship program, the CTU Global Postdoc Fellowship. This new and attractive two-year fellowship-program offers excellent researchers who have rec...

I have an opening for a two years post-doc position on instance-level (personalized) visual generation. Eligibility: (i) <=7 years from Ph.D. (ii) studies or 1 year outside of Czechia (ii) >=3 journal with IF or CORE A*/A conference papers. Deadline: 15 Feb.
Details: www.euraxess.cz/jobs/399390

🚀New task: Instance-level Image+Text→Image Retrieval

🔎Given a query image + an edit (“during night”), retrieve the same specific instance after the change — not just any similar object.

🛢New dataset on HF: i-CIR huggingface.co/datasets/bil...

🔥Download, run, and share results!

12/12 Joint work with Giorgos Petsangourakis, Christos Sgouropoulos, Theodoros Giannakopoulos, Giorgos Sfikas, @ikakogeorgiou.bsky.social.

REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion Latent diffusion models (LDMs) achieve state-of-the-art image synthesis, yet their reconstruction-style denoising objective provides only indirect semantic supervision: high-level semantics emerge slo...

11/n Summary🏁

REGLUE shows that the way we leverage VFM semantics matters for diffusion. Combining compact local semantics with global context yields faster convergence and state-of-the-art image generation.

📄arXiv: arxiv.org/abs/2512.16636
💻Project: reglueyourlatents.github.io

10/n Faster convergence🔥

REGLUE (SiT-B/2) achieves 12.9 and 28.7 FID at 400K iterations in conditional and unconditional generation, respectively, outperforming REPA, ReDi, and REG. REGLUE (SiT-XL/2) matches 1M-step SOTA performance in just 700k iterations (~30% fewer steps).

9/n Alignment effects ⚓

External alignment complements joint modeling, but its benefits depend on the signal. Local alignment yields consistent gains, whereas global-only alignment can degrade performance. Spatial joint modeling remains the primary driver.

8/n Local > Global Semantics🧩

Our analysis shows that jointly modeling with patch-level semantics drives most gains. The global [CLS] helps, but fine-grained spatial features deliver a strongly larger FID improvement, highlighting the importance of local structure for diffusion.