Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation
Image-level weakly supervised semantic segmentation is a challenging problem that has
been deeply studied in recent years. Most of advanced solutions exploit class activation map …
been deeply studied in recent years. Most of advanced solutions exploit class activation map …
Deep spectral methods: A surprisingly strong baseline for unsupervised semantic segmentation and localization
L Melas-Kyriazi, C Rupprecht… - Proceedings of the …, 2022 - openaccess.thecvf.com
Unsupervised localization and segmentation are long-standing computer vision challenges
that involve decomposing an image into semantically-meaningful segments without any …
that involve decomposing an image into semantically-meaningful segments without any …
[PDF][PDF] Deep vit features as dense visual descriptors
S Amir, Y Gandelsman, S Bagon… - ar**_CVPR_2020_paper.pdf" data-clk="hl=en&sa=T&oi=gga&ct=gga&cd=8&d=4814751788358432668&ei=qhelZ5_uD9abieoPjsC_yAM" data-clk-atid="nPfH6j1v0UIJ" target="_blank">[PDF] thecvf.com
Interpretable and accurate fine-grained recognition via region grou**
We present an interpretable deep model for fine-grained visual recognition. At the core of
our method lies the integration of region-based part discovery and attribution within a deep …
our method lies the integration of region-based part discovery and attribution within a deep …
Repurposing gans for one-shot semantic part segmentation
N Tritrong, P Rewatbowornwong… - Proceedings of the …, 2021 - openaccess.thecvf.com
While GANs have shown success in realistic image generation, the idea of using GANs for
other tasks unrelated to synthesis is underexplored. Do GANs learn meaningful structural …
other tasks unrelated to synthesis is underexplored. Do GANs learn meaningful structural …