C2am: Contrastive learning of class-agnostic activation map for weakly supervised object localization and semantic segmentation
While class activation map (CAM) generated by image classification network has been
widely used for weakly supervised object localization (WSOL) and semantic segmentation …
widely used for weakly supervised object localization (WSOL) and semantic segmentation …
Discriminative sounding objects localization via self-supervised audiovisual matching
Discriminatively localizing sounding objects in cocktail-party, ie, mixed sound scenes, is
commonplace for humans, but still challenging for machines. In this paper, we propose a two …
commonplace for humans, but still challenging for machines. In this paper, we propose a two …
Semantics meets temporal correspondence: Self-supervised object-centric learning in videos
Self-supervised methods have shown remarkable progress in learning high-level semantics
and low-level temporal correspondence. Building on these results, we take one step further …
and low-level temporal correspondence. Building on these results, we take one step further …
Motion-aware contrastive video representation learning via foreground-background merging
In light of the success of contrastive learning in the image domain, current self-supervised
video representation learning methods usually employ contrastive loss to facilitate video …
video representation learning methods usually employ contrastive loss to facilitate video …
Large-scale unsupervised object discovery
Existing approaches to unsupervised object discovery (UOD) do not scale up to large
datasets without approximations that compromise their performance. We propose a novel …
datasets without approximations that compromise their performance. We propose a novel …
Self-supervised object detection from audio-visual correspondence
We tackle the problem of learning object detectors without supervision. Differently from
weakly-supervised object detection, we do not assume image-level class labels. Instead, we …
weakly-supervised object detection, we do not assume image-level class labels. Instead, we …
Class-aware sounding objects localization via audiovisual correspondence
Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to
discriminatively localize different sounding objects but quite challenging for machines to …
discriminatively localize different sounding objects but quite challenging for machines to …
Contrastive learning of class-agnostic activation map for weakly supervised object localization and semantic segmentation
While class activation map (CAM) generated by image classification network has been
widely used for weakly supervised object localization (WSOL) and semantic segmentation …
widely used for weakly supervised object localization (WSOL) and semantic segmentation …
Complementary parts contrastive learning for fine-grained weakly supervised object co-localization
L Ma, F Zhao, H Hong, L Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The aim of weakly supervised object co-localization is to locate different objects of the same
superclass in a dataset. Recent methods achieve impressive co-localization performance by …
superclass in a dataset. Recent methods achieve impressive co-localization performance by …
Towards learning spatially discriminative feature representations
The backbone of traditional CNN classifier is generally considered as a feature extractor,
followed by a linear layer which performs the classification. We propose a novel loss …
followed by a linear layer which performs the classification. We propose a novel loss …