Search Results for author:
Found 12 papers, 8 papers with code
Rethinking Patch Dependence for Masked Autoencoders
In this work, we re-examine inter-patch dependencies in the decoding mechanism of masked autoencoders (MAE).
Unsupervised Universal Image Segmentation
Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e. g., STEGO) or class-agnostic instance segmentation (e. g., CutLER), but not both (i. e., panoptic segmentation).
Ranked #1 on
Unsupervised Panoptic Segmentation
on COCO val2017
Self-correcting LLM-controlled Diffusion Models
Steered by an LLM controller, SLD turns text-to-image generation into an iterative closed-loop process, ensuring correctness in the resulting image.
LLM-grounded Video Diffusion Models
We show that LLMs are able to understand complex spatiotemporal dynamics from text alone and generate layouts that align closely with both the prompts and the object motion patterns typically observed in the real world.
LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
Our method significantly outperforms the base diffusion model and several strong baselines in accurately generating images according to prompts that require various capabilities, doubling the generation accuracy across four tasks on average.
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping
The Gestalt law of common fate, i. e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation.
Ranked #1 on
Unsupervised Object Segmentation
on FBMS-59
Q-Diffusion: Quantizing Diffusion Models
We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture of the diffusion models, which compresses the noise estimation network to accelerate the generation process.
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy
Previous methods in unsupervised video object segmentation (UVOS) have demonstrated the effectiveness of motion as either input or supervision for segmentation.
Debiased Learning from Naturally Imbalanced Pseudo-Labels
Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data.
Ranked #1 on
Few-Shot Image Classification
on ImageNet - 0-Shot
(using extra training data)
Unsupervised Selective Labeling for More Effective Semi-Supervised Learning
Intuitively, no matter what the downstream task is, instances to be labeled must be representative and diverse: The former would facilitate label propagation to unlabeled data, whereas the latter would ensure coverage of the entire dataset.
Active Learning
Semi-Supervised Image Classification (Cold Start)
Unsupervised Visual Attention and Invariance for Reinforcement Learning
Existing methods focus on training an RL policy that is universal to changing visual domains, whereas we focus on extracting visual foreground that is universal, feeding clean invariant vision to the RL policy learner.
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and larger confusion with hard negatives for the tail.
Ranked #22 on
Long-tail Learning
on iNaturalist 2018
