arXiv:2608. 11123v1 Announce Type: cross Abstract: Augmentation can corrupt a training example when an image and its annotations receive different random changes.
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: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: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: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: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: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.
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. 06929v1 Announce Type: cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability.
arXiv:2606. 07638v1 Announce Type: cross Abstract: Image generative models, though widely used as creative tools, offer limited support for the kind of compositional control that photographers and visual artists routinely exercise.
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
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. 12704v1 Announce Type: cross Abstract: Multi-label classification assigns several co-occurring labels to each aerial scene, yet deployed models often encounter data distributions different from their training.