Adversarial complementary learning for weakly supervised object localization
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically
localize integral objects of semantic interest with weak supervision. We first mathematically …
localize integral objects of semantic interest with weak supervision. We first mathematically …
Underwater image co-enhancement with correlation feature matching and joint learning
Q Qi, Y Zhang, F Tian, QMJ Wu, K Li… - … on Circuits and …, 2021 - ieeexplore.ieee.org
In underwater scenes, degraded underwater images caused by wavelength-dependent light
absorption and scattering present huge challenges to vision tasks. Underwater image …
absorption and scattering present huge challenges to vision tasks. Underwater image …
Detection of co-salient objects by looking deep and wide
In this paper, we propose a unified co-salient object detection framework by introducing two
novel insights:(1) looking deep to transfer higher-level representations by using the …
novel insights:(1) looking deep to transfer higher-level representations by using the …
[HTML][HTML] Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework
Weakly supervised object detection is an interesting yet challenging research topic in
computer vision community, which aims at learning object models to localize and detect the …
computer vision community, which aims at learning object models to localize and detect the …
Revisiting co-saliency detection: A novel approach based on two-stage multi-view spectral rotation co-clustering
With the goal of discovering the common and salient objects from the given image group, co-
saliency detection has received tremendous research interest in recent years. However, as …
saliency detection has received tremendous research interest in recent years. However, as …
Few-shot open-set recognition using meta-learning
The problem of open-set recognition is considered. While previous approaches only
consider this problem in the context of large-scale classifier training, we seek a unified …
consider this problem in the context of large-scale classifier training, we seek a unified …
Making a case for 3d convolutions for object segmentation in videos
The task of object segmentation in videos is usually accomplished by processing
appearance and motion information separately using standard 2D convolutional networks …
appearance and motion information separately using standard 2D convolutional networks …
Stem-seg: Spatio-temporal embeddings for instance segmentation in videos
Existing methods for instance segmentation in videos typically involve multi-stage pipelines
that follow the tracking-by-detection paradigm and model a video clip as a sequence of …
that follow the tracking-by-detection paradigm and model a video clip as a sequence of …
Rough set based semi-supervised feature selection via ensemble selector
Similar to feature selection over completely labeled data, the aim of feature selection over
partially labeled data (semi-supervised feature selection) is also to find a feature subset …
partially labeled data (semi-supervised feature selection) is also to find a feature subset …
We don't need no bounding-boxes: Training object class detectors using only human verification
Training object class detectors typically requires a large set of images in which objects are
annotated by bounding-boxes. However, manually drawing bounding-boxes is very time …
annotated by bounding-boxes. However, manually drawing bounding-boxes is very time …