Serge Belongie

55

Papers

129

Total Citations

Papers (55)

Residual Networks Behave Like Ensembles of Relatively Shallow Networks

NeurIPS 2016arXiv

Rethinking Few-shot 3D Point Cloud Semantic Segmentation

Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy

From Coarse to Fine-Grained Open-Set Recognition

Coarse-To-Fine Tensor Trains for Compact Visual Representations

Building a Bird Recognition App and Large Scale Dataset With Citizen Scientists: The Fine Print in Fine-Grained Dataset Collection

Learning Deep Representations for Ground-to-Aerial Geolocalization

Fine-Grained Categorization and Dataset Bootstrapping Using Deep Metric Learning With Humans in the Loop

Learning to Match Aerial Images With Deep Attentive Architectures

Conditional Similarity Networks

Learning From Noisy Large-Scale Datasets With Minimal Supervision

Feature Pyramid Networks for Object Detection

Detecting Oriented Text in Natural Images by Linking Segments

Kernel Pooling for Convolutional Neural Networks

Stacked Generative Adversarial Networks

Lean Multiclass Crowdsourcing

DOTA: A Large-Scale Dataset for Object Detection in Aerial Images

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Generative Adversarial Perturbations

Learning to Evaluate Image Captioning

Separating Self-Expression and Visual Content in Hashtag Supervision

Controllable Video Generation With Sparse Trajectories

The INaturalist Species Classification and Detection Dataset

Class-Balanced Loss Based on Effective Number of Samples

End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection

DualSDF: Semantic Shape Manipulation Using a Two-Level Representation

Stay Positive: Non-Negative Image Synthesis for Augmented Reality

Intentonomy: A Dataset and Study Towards Human Intent Understanding

Benchmarking Representation Learning for Natural World Image Collections

On Feature Normalization and Data Augmentation

Spatiotemporal Contrastive Video Representation Learning

When Does Contrastive Visual Representation Learning Work?

Learning Concept Embeddings With Combined Human-Machine Expertise

Learning Visual Clothing Style With Heterogeneous Dyadic Co-Occurrences

BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography

Arbitrary Style Transfer in Real-Time With Adaptive Instance Normalization

PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows

Enhancing Adversarial Example Transferability With an Intermediate Level Attack

GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds

Exploring Visual Engagement Signals for Representation Learning

Robustness and Generalization via Generative Adversarial Training

Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

Learning Gradient Fields for Shape Generation

A Metric Learning Reality Check

Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset

On Label Granularity and Object Localization

Visual Prompt Tuning

Discriminative Class Tokens for Text-to-Image Diffusion Models

Taxonomy-Aware Evaluation of Vision-Language Models

Positional Normalization

Geometry Processing with Neural Fields

Implicit Neural Representations with Levels-of-Experts

Polynomial Neural Fields for Subband Decomposition and Manipulation

Learning to Taste: A Multimodal Wine Dataset