Mixed Barlow Twins aims to improve sample interaction during Barlow Twins training via linearly interpolated samples.Pre-training with this regularization effectively mitigates feature overfitting and further enhances the downstream performance on CIFAR-10, CIFAR-100, TinyImageNet, STL-10, and ImageNet datasets.

Attention Prompt Tuning (APT) is a computationally efficient variant of prompt tun- ing for video-based applications such as action recognition.

We propose using conditional diffusion models to predict density maps, as diffusion models are known to model complex distributions well and show high fidelity to training data during crowd-density map generation.

We propose AdaMAE, a novel, adaptive, and end-to-end trainable token sampling strategy for MAEs that takes into account the spatiotemporal properties of all input tokens to sample fewer but informative tokens.

Our method can unite multiple diffusion models trained on multiple sub-tasks and conquer the combined task through our proposed sampling strategy.

We propose a novel way to learn the representations from off-the-shelf, unlabeled remote sensing images available by various Earth observation programs through the diffusion process.

We propose a novel transformer network called HyperTransformer for HS pansharpening which achieves significant improvements over SOTA approaches. To the best of our knowledge, we are one of the first to introduce fusion transformer architecture for HS pansharpening.

We propose an orientation-guided graph convolutional network to improve connectivity while segmenting the bone surface.

We presents a transformer-based Siamese network architecture for Change Detection (CD) from a pair of co-registered remote sensing images. The proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD.

We propose a Spatial and Interaction Space Graph Reasoning (SPIN) module which when plugged into a ConvNet performs reasoning over graphs constructed on spatial and interaction spaces projected from the feature maps.

We proposed a novel approach for HS pansharpening, which mainly consists of three steps: (1) Upsampling the LR-HSI via DIP, (2) Predicting the residual image via over-complete HyperKite, and (3) Obtaining the final fused HSI by summation.

We propose a semi-supervised CD paradigm based on consistency regularization. The proposed approach can effectively leverage the information from freely-available, unlabeled, multi-temporal, remote-sensing images to enhance the CD performance.

We propose a despeckling network comprises of a transformer-based encoder which allows the network to learn global dependencies between different image regions - aiding in better despeckling.