SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.
Understanding contrastive representation learning through alignment and uniformity on the hypersphere.ArXiv, abs/2005.10242, 2020
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
SkyPart uses learnable prototypes for patch grouping, altitude modulation only in training, graph-attention readout, and Kendall-weighted loss to set new state-of-the-art single-pass performance on SUES-200, University-1652, and DenseUAV while widening gains under weather corruptions.
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
The NTIRE 2026 challenge provides a dataset of over 294,000 real and AI-generated images with 36 transformations to benchmark robust detection models.
The NTIRE 2026 challenge finds that large foundation models combined with ensembles and degradation-aware training produce the most robust deepfake detectors.
citing papers explorer
-
SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning
SMA uses a submodular mutual information objective on data sets to deliver competitive zero-shot classification and retrieval performance on CLIP benchmarks with only tens of thousands of samples, orders of magnitude fewer than standard approaches.
-
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
SkyPart uses learnable prototypes for patch grouping, altitude modulation only in training, graph-attention readout, and Kendall-weighted loss to set new state-of-the-art single-pass performance on SUES-200, University-1652, and DenseUAV while widening gains under weather corruptions.
-
Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
-
NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild
The NTIRE 2026 challenge provides a dataset of over 294,000 real and AI-generated images with 36 transformations to benchmark robust detection models.
-
Robust Deepfake Detection, NTIRE 2026 Challenge: Report
The NTIRE 2026 challenge finds that large foundation models combined with ensembles and degradation-aware training produce the most robust deepfake detectors.