Gabriele Trivigno @gabtriv.bsky.social · 07/04/2026(v) INSID3 outperforms both training free methods relying on SAM, and fine-tuned approaches, which fall short out-of-domain, demonstrating strong generalization across tasks and domains. 020
Gabriele Trivigno @gabtriv.bsky.social · 07/04/2026(iv) INSID3 removes it in a training-free way: we identify the positional component of DINOv3 features and project onto its orthogonal complement. 110
Gabriele Trivigno @gabtriv.bsky.social · 07/04/2026(iii) Besides semantic matches, DINOv3 also responds to absolute image position. Given a patch on the bird’s tail in the reference image, the DINOv3 similarity map activates on (i) the tail in the target image, but also (ii) over the left portion of the image. 110
Gabriele Trivigno @gabtriv.bsky.social · 07/04/2026(ii) Dense DINOv3 features naturally induce a structured decomposition of the scene. By clustering them, we obtain coherent object- and part-level regions without supervision. 110
Gabriele Trivigno @gabtriv.bsky.social · 07/04/2026🔥 Can in-context segmentation emerge directly from frozen DINOv3 features? At #CVPR2026, we present INSID3: Training-Free In-Context Segmentation with DINOv3 — a collaboration between PoliTo, TU Darmstadt and TU Munich. Check it out: github.com/visinf/INSID3 1136
Gabriele Trivigno @gabtriv.bsky.social · 02/06/2025📄 Read the full paper: SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation Now on arXiv → arxiv.org/abs/2505.21795 000
Gabriele Trivigno @gabtriv.bsky.social · 02/06/2025🔹 4/4 – Promptable segmentation in action SANSA reduces reliance on costly pixel-level masks by supporting point, box, and scribble prompts 📈enabling fast, scalable annotation with minimal supervision. See the qualitative results 👇 100
Gabriele Trivigno @gabtriv.bsky.social · 02/06/2025🔹 3/4 – SANSA achieves state-of-the-art in few-shot segmentation. We outperform specialist and foundation-based methods across various benchmarks: 📈 +9.3% mIoU on LVIS-92i ⚡ 3× faster than prior works 💡 Only 234M parameters (4-5x smaller than competitors) 100
Gabriele Trivigno @gabtriv.bsky.social · 02/06/2025🔹2/4 – Unlocking semantic structure SAM2 features are rich, but optimized for tracking. 🧠 Insert bottleneck adapters into frozen SAM2 📉 These restructure feature space to disentangle semantics 📈 Result: features cluster semantically—even for unseen classes (see PCA👇) 100
Gabriele Trivigno @gabtriv.bsky.social · 02/06/2025🚀 As #CVPR2025 week kicks off, meet SANSA: Semantically AligNed Segment Anything 2 We turn SAM2 into a semantic few-shot segmenter: 🧠 Unlocks latent semantics in frozen SAM2 ✏️ Supports any prompt: fast and scalable annotation 📦 No extra encoders 📎 github.com/ClaudiaCutta... 100
Gabriele Trivigno @gabtriv.bsky.social · 11/05/2025I guess merging the events could also work 😂 I wonder whether cricket players would be better at ComputerVision than CV researchers are at cricket, or viceversa 010
Reposted by Gabriele TrivignoDmytro Mishkin @ducha-aiki.bsky.social · 11/04/2025To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition Davide Sferrazza, @berton-gabri.bsky.social Gabriele Trivigno, Carlo Masone tl;dr: global descriptors nowadays are often better than local feature matching methods for simple datasets. arxiv.org/abs/2504.06116 0112
Gabriele Trivigno @gabtriv.bsky.social · 10/04/2025✨ SAMWISE achieves state-of-the-art performance across multiple #RVOS benchmarks—while being the smallest model in RVOS! 🎯 It also sets a new #SOTA in image-level referring #segmentation. With only 4.9M trainable parameters, it runs #online and requires no fine-tuning of SAM2 🚀 000
Gabriele Trivigno @gabtriv.bsky.social · 10/04/2025🚀 Contributions: 🔹 Textual Prompts for SAM2: Early fusion of visual-text cues via a novel adapter 🔹 Temporal Modeling: Essential for video understanding, beyond frame-by-frame object tracking 🔹 Tracking Bias: Correcting tracking bias in SAM2 for text-aligned object discovery 100
Gabriele Trivigno @gabtriv.bsky.social · 10/04/2025🔥 Our paper SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation is accepted as a #Highlight at #CVPR2025! 🎉 We make #SegmentAnything wiser, enabling it to understand textual prompts—training only 4.9M parameters! 🧠 💻 Code, models & demo: github.com/ClaudiaCutta... Why SAMWISE?👇 120
Reposted by Gabriele TrivignoZhenjun Zhao @ericzzj.bsky.social · 09/04/2025To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition Davide Sferrazza, @berton-gabri.bsky.social, @gabtriv.bsky.social, Carlo Masone tl;dr:VPR datasets saturate;re-ranking not good;image matching->uncertainty->inlier counts->confidence arxiv.org/abs/2504.06116 052
Reposted by Gabriele TrivignoGabriele Berton @berton-gabri.bsky.social · 18/03/2025🚀 Paper Release! 🚀 Curious about image retrieval and contrastive learning? We present: 📄 "All You Need to Know About Training Image Retrieval Models" 🔍 The most comprehensive retrieval benchmark—thousands of experiments across 4 datasets, dozens of losses, batch sizes, LRs, data labeling, and more! 24010
Gabriele Trivigno @gabtriv.bsky.social · 07/04/2025Trying to convince my bluesky feed to put me in the Computer Vision community. Right now I only see posts about the orange-haired president. @berton-gabri.bsky.social @gabrigole.bsky.social how did you do it? 100
Reposted by Gabriele Trivignotommiekerssies.bsky.social @tommiekerssies.bsky.social · 31/03/2025Image segmentation doesn’t have to be rocket science. 🚀 Why build a rocket engine full of bolted-on subsystems when one elegant unit does the job? 💡 That’s what we did for segmentation. ✅ Meet the Encoder-only Mask Transformer (EoMT): tue-mps.github.io/eomt (CVPR 2025) (1/6) 184
Gabriele Trivigno @gabtriv.bsky.social · 05/04/2025Went outside today and thought this would be perfect for my first #bluesky post 010
