Search Results for author:
Found 40 papers, 19 papers with code
Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
Precise manipulation that is generalizable across scenes and objects remains a persistent challenge in robotics.
Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps
To address these limitations, we propose a new approach for semantic correspondence estimation that supplements discriminative self-supervised features with 3D understanding via a weak geometric spherical prior.
Active Learning-Based Species Range Estimation
Our results demonstrate that our method outperforms alternative active learning methods and approaches the performance of end-to-end trained models, even when only using a fraction of the data.
Spatial Implicit Neural Representations for Global-Scale Species Mapping
Estimating the geographical range of a species from sparse observations is a challenging and important geospatial prediction problem.
VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations
We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries.
Virtual Occlusions Through Implicit Depth
We instead propose an implicit model for depth and use that to predict the occlusion mask directly.
Incremental Generalized Category Discovery
We explore the problem of Incremental Generalized Category Discovery (IGCD).
Self-Supervised Multimodal Learning: A Survey
In this survey, we provide a comprehensive review of the state-of-the-art in SSML, in which we elucidate three major challenges intrinsic to self-supervised learning with multimodal data: (1) learning representations from multimodal data without labels, (2) fusion of different modalities, and (3) learning with unaligned data.
SAOR: Single-View Articulated Object Reconstruction
We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild.
Vision Learners Meet Web Image-Text Pairs
In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.
ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation
Understanding the 3D world without supervision is currently a major challenge in computer vision as the annotations required to supervise deep networks for tasks in this domain are expensive to obtain on a large scale.
ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fields
We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimation method that learns to predict category-level viewpoints directly from images during training.
An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
In practice, a given video can contain multiple valid positive annotations for the same action.
SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
To combat this, a series of light-weight adaptation methods have been proposed to efficiently adapt such models when limited supervision is available.
Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset
We thoroughly benchmark audiovisual classification performance and modality fusion experiments through the use of state-of-the-art transformer methods.
Visual Knowledge Tracing
In this work, we propose a novel task of tracing the evolving classification behavior of human learners as they engage in challenging visual classification tasks.
On Label Granularity and Object Localization
Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels.
Demystifying Unsupervised Semantic Correspondence Estimation
We explore semantic correspondence estimation through the lens of unsupervised learning.
Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost.
Fine-Grained Image Analysis with Deep Learning: A Survey
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications.
Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring
We address the problem of learning self-supervised representations from unlabeled image collections.
Multi-Label Learning from Single Positive Labels
When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image.
When Does Contrastive Visual Representation Learning Work?
Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification.
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
We propose ManyDepth, an adaptive approach to dense depth estimation that can make use of sequence information at test time, when it is available.
Monocular Depth Estimation
Unsupervised Monocular Depth Estimation
Benchmarking Representation Learning for Natural World Image Collections
In order to facilitate progress in this area we present two new natural world visual classification datasets, iNat2021 and NeWT.
Learning Stereo from Single Images
We propose that it is unnecessary to have such a high reliance on ground truth depths or even corresponding stereo pairs.
Geocoding of trees from street addresses and street-level images
We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching.
Presence-Only Geographical Priors for Fine-Grained Image Classification
Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories.
The iWildCam 2018 Challenge Dataset
Camera traps are a valuable tool for studying biodiversity, but research using this data is limited by the speed of human annotation.
Digging Into Self-Supervised Monocular Depth Estimation
Per-pixel ground-truth depth data is challenging to acquire at scale.
Ranked #3 on
Monocular Depth Estimation
on VA (Virtual Apartment)
Teaching Multiple Concepts to a Forgetful Learner
Our framework is both generic, allowing the design of teaching schedules for different memory models, and also interactive, allowing the teacher to adapt the schedule to the underlying forgetting mechanisms of the learner.
It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data.
Teaching Categories to Human Learners with Visual Explanations
We study the problem of computer-assisted teaching with explanations.
Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners
We highlight that adaptivity does not speed up the teaching process when considering existing models of version space learners, such as "worst-case" (the learner picks the next hypothesis randomly from the version space) and "preference-based" (the learner picks hypothesis according to some global preference).
Context Embedding Networks
Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications.
The iNaturalist Species Classification and Detection Dataset
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.
Ranked #8 on
Image Classification
on iNaturalist
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Learning based methods have shown very promising results for the task of depth estimation in single images.
Ranked #4 on
Monocular Depth Estimation
on Mid-Air Dataset
Structured Prediction of Unobserved Voxels From a Single Depth Image
Building a complete 3D model of a scene, given only a single depth image, is underconstrained.
Hierarchical Subquery Evaluation for Active Learning on a Graph
Under some specific circumstances, Expected Error Reduction has been one of the strongest-performing informativeness criteria for active learning.
Becoming the Expert - Interactive Multi-Class Machine Teaching
However, image-importance is individual-specific, i. e. a teaching image is important to a student if it changes their overall ability to discriminate between classes.
