Deep learning for weakly-supervised object detection and localization: A survey
Abstract Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), ie.,
detecting multiple and single instances with bounding boxes in an image using image-level …
detecting multiple and single instances with bounding boxes in an image using image-level …
Fairness-aware contrastive learning with partially annotated sensitive attributes
Learning high-quality representation is important and essential for visual recognition.
Unfortunately, traditional representation learning suffers from fairness issues since the …
Unfortunately, traditional representation learning suffers from fairness issues since the …
Active learning for point cloud semantic segmentation via spatial-structural diversity reasoning
The expensive annotation cost is notoriously known as the main constraint for the
development of the point cloud semantic segmentation technique. Active learning methods …
development of the point cloud semantic segmentation technique. Active learning methods …
Causal interventional training for image recognition
Deep learning models often fit undesired dataset bias in training. In this paper, we formulate
the bias using causal inference, which helps us uncover the ever-elusive causalities among …
the bias using causal inference, which helps us uncover the ever-elusive causalities among …
Nicest: Noisy label correction and training for robust scene graph generation
Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth
annotation qualities of mainstream SGG datasets, ie, they assume: 1) all the manually …
annotation qualities of mainstream SGG datasets, ie, they assume: 1) all the manually …
Weakly-supervised video object grounding via causal intervention
We target at the task of weakly-supervised video object grounding (WSVOG), where only
video-sentence annotations are available during model learning. It aims to localize objects …
video-sentence annotations are available during model learning. It aims to localize objects …
SPA2Net: Structure-Preserved Attention Activated Network for Weakly Supervised Object Localization
By exploring the localizable representations in deep CNN, weakly supervised object
localization (WSOL) methods could determine the position of the object in each image just …
localization (WSOL) methods could determine the position of the object in each image just …
Fdcnet: Feature drift compensation network for class-incremental weakly supervised object localization
This work addresses the task of class-incremental weakly supervised object localization (CI-
WSOL). The goal is to incrementally learn object localization for novel classes using only …
WSOL). The goal is to incrementally learn object localization for novel classes using only …
Improving weakly supervised sound event detection with causal intervention
Existing weakly supervised sound event detection (WSSED) work has not explored both
types of co-occurrences simultaneously, ie, some sound events often co-occur, and their …
types of co-occurrences simultaneously, ie, some sound events often co-occur, and their …
Semantic-constraint matching transformer for weakly supervised object localization
Weakly supervised object localization (WSOL) strives to learn to localize objects with only
image-level supervision. Due to the local receptive fields generated by convolution …
image-level supervision. Due to the local receptive fields generated by convolution …