paper-with-me

Data Augmentation

3개 벤치마크 · 논문 9,655편 · 이 태스크의 논문 보기 →

Benchmarks

ImageNet

결과 19개

CIFAR-10

결과 5개

GA1457

결과 4개

Most implemented

Papers

Isotropic Embedding Perturbations for Robust Vision Language Encoders

2026-09-09 · Hyesong Choi, Daeun Kim, Song Park, Taekyung Kim 외 arxiv

Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer strong regularization effects, their combine…

Data Augmentation

Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials

2026-09-04 · Bumju Kwak, Jeonghee Jo arxiv

While machine-learning interatomic potentials (MLIPs) have successfully learned potential energy surfaces (PES) and atomic forces, many practical applications, such as vibrational analysis and transition state search, re…

Data Augmentation

REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation

2026-08-31 · Haoran Que, Jiajun Shi, Ting Huang, Renming Pang 외 arxiv

As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token prediction supervises what follows a context but leaves the intermediate …

Data Augmentation

AQ3D: Adaptive Query Transformer for 3D Instance Segmentation

2026-08-31 · Keno Moenck, Thorsten Schüppstuhl arxiv

Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training distribution rather than on the scene at hand. Indoor scans vary wi…

3D Instance SegmentationData Augmentation

Cross-Spectral Dense Correspondence for Multimodal Spectral Medical Imaging

2026-08-28 · Eric L. Wisotzky, Jost Triller, Simon W. Härtl, Oliver T. Bruns 외 arxiv

Precise dense correspondence is a fundamental prerequisite for multimodal spectral imaging systems that fuse disparate wavelength ranges for subsequent analysis in medical and scientific imaging. Corresponding image poin…

Data Augmentation

Physics-Guided Flow Matching for CT Image Reconstruction

2026-08-28 · Davide Evangelista arxiv

Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion mode…

Computational EfficiencyImage ReconstructionData Augmentation

전체 9,655편 보기 →