Computer Vision

aTLAS: a novel parameter-efficient fine-tuning method using learned anisotropic scaling of task vectors for enhanced knowledge composition and transfer.

Key-Grid: An unsupervised 3D keypoint detector achieving state-of-the-art semantic consistency and accuracy for both rigid and deformable objects using novel grid heatmap features.

Boost 3D object detection accuracy by augmenting pseudo-LiDAR point clouds!

Pixelsmith: Generate gigapixel images with a single GPU, surpassing limitations of existing methods through a cascading approach and innovative guidance mechanism.

PASTA: A novel modular framework boosts MOT tracker generalization by using parameter-efficient fine-tuning and avoiding negative interference through specialized modules for various scenario attribut…

IR-CM: One-step image restoration using a novel consistency model for fast and universal performance.

IODA achieves efficient one-shot domain adaptation for super-resolution using a novel instance-guided strategy and image-level domain alignment, significantly improving performance with limited target…

Invertible Consistency Distillation (iCD) achieves high-quality image editing in ~7 steps by enabling both fast editing and strong generation using a generalized distillation framework and dynamic cla…

Researchers model a manifold of customized diffusion models as a subspace of weights, enabling controllable creation of new models via sampling, editing, and inversion from a single image.

Interpretable lightweight transformers are built by unrolling graph smoothness priors, achieving high performance with significantly fewer parameters than conventional transformers.

ProtoViT: a novel interpretable image classification method using Vision Transformers and adaptive prototypes, achieving higher accuracy and providing clear explanations.

Deep metric learning and Coreset integration enables efficient slice-based active learning for 3D medical segmentation, surpassing existing methods in performance with low annotation budgets.

LeTs: Learnable Transformation efficiently initializes variable-sized Vision Transformers by learning adaptable transformations from a compact learngene module, outperforming from-scratch training.

InfiNet achieves state-of-the-art results by enabling feature interaction in an infinite-dimensional space using RBF kernels, surpassing models limited to finite-dimensional interactions.

This research presents LocalN2NM, a novel method for inferring neural signed distance functions (SDF) from single, noisy point clouds by finetuning data-driven priors, achieving faster inference and b…

Meta-learning enhances human mesh recovery by unifying training and test-time objectives, significantly improving accuracy and generalization.

In-N-Out: Lifting 2D Diffusion Priors for 3D Object Removal via Tuning-Free Latents Alignment enhances 3D scene reconstruction by aligning 2D diffusion model latents for consistent multi-view inpainti…

CONTEXTSSL: A novel self-supervised learning algorithm that adapts to task-specific symmetries by using context, achieving significant performance gains over existing methods.

This research leverages causal intervention to identify and utilize genuine label correlations in multi-label image recognition, mitigating contextual bias for improved accuracy.

Active Viewpoint Selection (AVS) significantly improves viewpoint-independent object-centric representations by actively selecting the most informative viewpoints for each scene, leading to better seg…