Search Results for author:
Found 8 papers, 4 papers with code
Optimization of Rank Losses for Image Retrieval
It provides an upperbound for rank losses and ensures robust training.
Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representations
In this work, we address the problem of universal image embedding, where a single universal model is trained and used in multiple domains.
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-VQA [37], yet it only achieves 13. 0% accuracy on our dataset.
Yes, we CANN: Constrained Approximate Nearest Neighbors for local feature-based visual localization
In this paper, we take a step back from this assumption and propose Constrained Approximate Nearest Neighbors (CANN), a joint solution of k-nearest-neighbors across both the geometry and appearance space using only local features.
LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals
Finding localized correspondences across different images of the same object is crucial to understand its geometry.
Improving Fairness in Large-Scale Object Recognition by CrowdSourced Demographic Information
We showcase its application to the landmark recognition domain, presenting a detailed analysis and the final fairer landmark rankings.
Towards A Fairer Landmark Recognition Dataset
To create a more comprehensive and equitable dataset, we start by defining the fair relevance of a landmark to the world population.
Class-Balanced Distillation for Long-Tailed Visual Recognition
An effective and simple approach to long-tailed visual recognition is to learn feature representations and a classifier separately, with instance and class-balanced sampling, respectively.
Ranked #11 on
Long-tail Learning
on iNaturalist 2018
