OrthoRF introduces orthogonality into Rotating Features (RF) by applying an inner-product loss and architectural changes, improving phase alignment and grouping reliability. The method outperforms or matches existing unsupervised object discovery models, especially in challenging scenarios such as overlapping objects, noise, and out-of-distribution tests. Additionally, OrthoRF can recover occluded object parts without requiring post-hoc clustering, producing more interpretable representations.
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
arXiv:2605. 07821v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models.
arXiv:2607. 02386v1 Announce Type: cross Abstract: While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood.
arXiv:2605.05556v2 Announce Type: replace Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...
ODSS-Net introduces a framework for multi‑modal object re‑identification that separates shared structural information from modality‑specific cues. It employs a Shared Structural Feature Construction module to extract modality‑shared structure, an Orthogonal Specific Feature Learning module to isolate identity‑relevant local features, and a Sample Adaptive Mixture of Experts module to fuse these features based on shared structure. Experiments on three benchmarks confirm the effectiveness of this orthogonally decoupled representation learning approach.
arXiv:2604. 07904v2 Announce Type: replace Abstract: Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding.
arXiv:2606. 03976v1 Announce Type: cross Abstract: Representations of the world, arguably, contain information about features (e.
arXiv:2607. 00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings.
arXiv:2607. 02404v1 Announce Type: cross Abstract: Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets.
arXiv:2609.37685v1 Announce Type: new Abstract: Language-aligned and self-supervised visual encoders offer complementary strengths in semantic abstraction and spatial detail. Harnessing this compleme...
arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.
The study investigates whether self‑supervised learning can produce useful representations from fMRI data alone. Using a joint embedding predictive architecture, participant‑specific encoders are trained without access to stimulus images or derived representations. The resulting embeddings perform competitively on brain captioning, image reconstruction, and cross‑participant generalization, and can be aligned unsupervised across participants, enabling a decoding head trained on one subject to work on another with minimal loss of performance.