arXiv:2606. 26734v1 Announce Type: cross Abstract: The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity.
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:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.
arXiv:2602. 18094v2 Announce Type: replace-cross Abstract: Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID).
arXiv:2510. 06596v2 Announce Type: replace-cross Abstract: The performance of machine learning models depends heavily on training data.
arXiv:2605. 07821v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models.
arXiv:2606. 11837v1 Announce Type: cross Abstract: Open-vocabulary scene sketch semantic segmentation aims to assign dense semantic labels to sparse line drawings based on flexible category vocabularies specified at inference time, without relying on pixel-level annotations during training.
arXiv:2608. 05424v1 Announce Type: cross Abstract: Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals.
arXiv:2410. 19553v2 Announce Type: replace-cross Abstract: This paper explores the impact of occlusions in video action detection.
arXiv:2608. 00716v1 Announce Type: cross Abstract: Robust detection of generated images is critical to counter the misuse of generative models.
arXiv:2607. 18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks.
arXiv:2607. 18195v1 Announce Type: cross Abstract: Vision models have been found to be susceptible to perturbations such as motion blur induced at runtime by a shaking camera.
arXiv:2606. 28551v1 Announce Type: cross Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies.