activity
20202023
most citedFaster Segment Anything: Towards Lightweight SAM for Mobile Applications

144 citations · 161 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2023

Internal-External Boundary Attention Fusion for Glass Surface Segmentation

Dongshen Han, Seungkyu Lee, Chaoning Zhang +4

Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of…

cs.CV2023★ 144 cited

Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Chaoning Zhang, Dongshen Han, Yu Qiao +4

Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like im…

cs.CV2023★ 13 cited

Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected

Dongsheng Han, Chaoning Zhang, Yu Qiao +5

Meta AI Research has recently released SAM (Segment Anything Model) which is trained on a large segmentation dataset of over 1 billion masks. As a foundation model in the field of…

cs.LG2021

Continual Learning with Neuron Activation Importance

Sohee Kim, Seungkyu Lee

Continual learning is a concept of online learning with multiple sequential tasks. One of the critical barriers of continual learning is that a network should learn a new task keep…

cs.CV2021★ 1 cited

Unrealistic Feature Suppression for Generative Adversarial Networks

Sanghun Kim, SeungKyu Lee

Due to the unstable nature of minimax game between generator and discriminator, improving the performance of GANs is a challenging task. Recent studies have shown that selected hig…

cs.LG2020

Sub-clusters of Normal Data for Anomaly Detection

Gahye Lee, Seungkyu Lee

Anomaly detection in data analysis is an interesting but still challenging research topic in real world applications. As the complexity of data dimension increases, it requires to…

cs.LG2020★ 1 cited

Mode Penalty Generative Adversarial Network with adapted Auto-encoder

Gahye Lee, Seungkyu Lee

Generative Adversarial Networks (GAN) are trained to generate sample images of interest distribution. To this end, generator network of GAN learns implicit distribution of real dat…

cs.CV2020★ 2 cited

Small Noisy and Perspective Face Detection using Deformable Symmetric Gabor Wavelet Network

Sherzod Salokhiddinov, Seungkyu Lee

Face detection and tracking in low resolution image is not a trivial task due to the limitation in the appearance features for face characterization. Moreover, facial expression gi…