Augmentation can corrupt a training example when an image and its annotations receive different random changes. A crop must use the same coordinates for the image, mask, boxes, keypoints, stereo views, video frames, or volume.
arXiv:2608. 11123v1 Announce Type: cross Abstract: Augmentation can corrupt a training example when an image and its annotations receive different random changes.
arXiv:2606. 04820v1 Announce Type: cross Abstract: CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic contribution to the mixed image.
arXiv:2606. 10713v1 Announce Type: cross Abstract: The nnU-Net has demonstrated continuous success in medical segmentation tasks, which heavily rely on the availability and diversity of annotated biomedical data.
arXiv:2503. 09399v4 Announce Type: replace-cross Abstract: Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific context.
arXiv:2608. 06929v1 Announce Type: cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability.
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:2509. 15357v3 Announce Type: replace-cross Abstract: Diffusion models have achieved strong results in text-to-image generation, but important limitations remain as prompts become more structured and multi-object.
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
arXiv:2608. 07570v1 Announce Type: cross Abstract: Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred.
Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Self-Flow, further remove the dependency on external pretrained encoders by constructing alignment within the diffusion model itself.
arXiv:2607. 08794v1 Announce Type: cross Abstract: Sand boils on earthen levees are safety-critical defects, but pixel-level detection is limited by scarce annotations.
arXiv:2608. 05424v1 Announce Type: cross Abstract: Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals.