Search Results for author:
Found 14 papers, 8 papers with code
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving
This necessitates an expensive process of continuously curating and annotating data with significant human effort.
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data
Semi-supervised learning aims to train a model using limited labels.
Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation
Inspired by this, we introduce a novel task, text-guided video completion (TVC), which requests the model to generate a video from partial frames guided by an instruction.
Ranked #3 on
Video Prediction
on BAIR Robot Pushing
Semi-Supervised Learning with Taxonomic Labels
We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains.
The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop
Semi-iNat is a challenging dataset for semi-supervised classification with a long-tailed distribution of classes, fine-grained categories, and domain shifts between labeled and unlabeled data.
A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes.
The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop
From this collection, we sample a subset of classes and their labels, while adding the images from the remaining classes to the unlabeled set of images.
On Equivariant and Invariant Learning of Object Landmark Representations
Given a collection of images, humans are able to discover landmarks by modeling the shared geometric structure across instances.
When Does Self-supervision Improve Few-shot Learning?
We investigate the role of self-supervised learning (SSL) in the context of few-shot learning.
Boosting Supervision with Self-Supervision for Few-shot Learning
We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions.
Active Adversarial Domain Adaptation
Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains.
A Deeper Look at 3D Shape Classifiers
We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations.
Reasoning about Fine-grained Attribute Phrases using Reference Games
We collect a large dataset of such phrases by asking annotators to describe several visual differences between a pair of instances within a category.
Adapting Models to Signal Degradation using Distillation
Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning.
