Search Results for author:
Found 8 papers, 3 papers with code
Blended Latent Diffusion under Attention Control for Real-World Video Editing
First, although existing methods attempt to focus on local area editing by a pre-defined mask, the preservation of the outside-area background is non-ideal due to the spatially entire generation of each frame.
Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization
By fine-tuning the ADClick-Seg model using the weak labels inferred by ADClick, we establish the state-of-the-art performances in supervised AD tasks (AP $= 86. 4\%$ on MVTec AD and AP $= 78. 4\%$, PRO $= 98. 6\%$ on KSDD2).
Ranked #3 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
Boosting Box-supervised Instance Segmentation with Pseudo Depth
This innovative approach empowers the network to simultaneously predict masks and depth, enhancing its ability to capture nuanced depth-related information during the instance segmentation process.
De novo protein design using geometric vector field networks
Most prior encoders rely on atom-wise features, such as angles and distances between atoms, which are not available in this context.
CTVIS: Consistent Training for Online Video Instance Segmentation
The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS).
Ranked #3 on
Video Instance Segmentation
on Youtube-VIS 2022 Validation
(using extra training data)
Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers
In this work, we propose a novel framework called "Weakly-supervised RESidual Transformer" (WeakREST), which aims to achieve high AD accuracy while minimizing the need for extensive annotations.
Ranked #1 on
Anomaly Detection
on BTAD
(using extra training data)
Asymmetric Cross-Scale Alignment for Text-Based Person Search
To implement this task, one needs to extract multi-scale features from both image and text domains, and then perform the cross-modal alignment.
T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up
Our architecture is orthogonal to StackGAN++ , and focuses on person image generation, with all of them together to enrich the spectrum of GANs for the image generation task.
