Search Results for author:
Found 10 papers, 7 papers with code
Improving Image Restoration through Removing Degradations in Textual Representations
To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations, and then convert the restored textual representations into a guidance image for assisting image restoration.
AiluRus: A Scalable ViT Framework for Dense Prediction
Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence.
From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
By simply equipping it with an MLP layer for alignment, DINO surpasses CLIP in fine-grained related perception tasks.
ControlVideo: Training-free Controllable Text-to-Video Generation
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling.
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation
Seed area generation is usually the starting point of weakly supervised semantic segmentation (WSSS).
Multi-Label Classification
Weakly supervised Semantic Segmentation
+1
SdAE: Self-distillated Masked Autoencoder
We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck.
A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Next, we summarize the existing label-efficient image segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction -- the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, and cross-image relation.
Understanding Self-supervised Learning via Information Bottleneck Principle
To address this issue, we introduce the information bottleneck principle and propose the Self-supervised Variational Information Bottleneck (SVIB) learning framework.
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis.
Ranked #3 on
Medical Image Segmentation
on ACDC
Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network
Without noise level parameter, our general noise-applicable model is also better than the other compared methods in two datasets.
