Search Results for author:
Found 10 papers, 9 papers with code
Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation
Specifically, we construct support and query prototypes with SAM features and distinguish query prototypes of target regions based on ResNet features.
Diverse Rare Sample Generation with Pretrained GANs
This study proposes a novel approach for generating diverse rare samples from high-resolution image datasets with pretrained GANs.
Mutually-Aware Feature Learning for Few-Shot Object Counting
Few-shot object counting has garnered significant attention for its practicality as it aims to count target objects in a query image based on given exemplars without the need for additional training.
Progressive Proxy Anchor Propagation for Unsupervised Semantic Segmentation
Then, considering the distribution of positive samples, we relocate the proxy anchor towards areas with a higher concentration of positives and adjust the positiveness boundary based on the propagation degree of the proxy anchor.
Mitigating Background Shift in Class-Incremental Semantic Segmentation
Additionally, in the case of the second approach, initializing the new class classifier with background knowledge triggers a similar background shift issue, but towards the new classes.
Ranked #1 on
Overlapped 5-3
on PASCAL VOC 2012
Task-Disruptive Background Suppression for Few-Shot Segmentation
Based on these two scores, we define a query background relevant score that captures the similarity between the backgrounds of the query and the support, and utilize it to scale support background features to adaptively restrict the impact of disruptive support backgrounds.
Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding
Dummy tokens conditioned by text query take portions of the attention weights, preventing irrelevant video clips from being represented by the text query.
Ranked #3 on
Highlight Detection
on TvSum
Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification
While TDM influences high-level feature maps by task-adaptive calibration of channel-wise importance, we further introduce Instance Attention Module (IAM) operating in intermediate layers of feature extractors to instance-wisely highlight object-relevant channels, by extending QAM.
Leveraging Hidden Positives for Unsupervised Semantic Segmentation
Specifically, we add the loss propagating to local hidden positives, semantically similar nearby patches, in proportion to the predefined similarity scores.
Ranked #3 on
Unsupervised Semantic Segmentation
on Potsdam-3
Task Discrepancy Maximization for Fine-grained Few-Shot Classification
Specifically, TDM learns task-specific channel weights based on two novel components: Support Attention Module (SAM) and Query Attention Module (QAM).
Ranked #11 on
Few-Shot Image Classification
on CUB 200 5-way 5-shot
(using extra training data)
