Search Results - "Lim, Ser Nam"

Detecting Everything in the Open World: Towards Universal Object Detection by Wang, Zhenyu, Li, Yali, Chen, Xi, Lim, Ser-Nam, Torralba, Antonio, Zhao, Hengshuang, Wang, Shengjin

“…In this paper, we formally address universal object detection, which aims to detect every scene and predict every category. The dependence on human…”
Get full text

Computationally Budgeted Continual Learning: What Does Matter? by Prabhu, Ameya, Al Kader Hammoud, Hasan Abed, Dokania, Puneet, Torr, Philip H.S., Lim, Ser-Nam, Ghanem, Bernard, Bibi, Adel

“…Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting…”
Get full text

Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning by Mukhoti, Jishnu, Lin, Tsung-Yu, Poursaeed, Omid, Wang, Rui, Shah, Ashish, Torr, Philip H.S., Lim, Ser-Nam

“…We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between…”
Get full text

Enhancing Adversarial Example Transferability With an Intermediate Level Attack by Huang, Qian, Katsman, Isay, Gu, Zeqi, He, Horace, Belongie, Serge, Lim, Ser-Nam

“…Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer,…”
Get full text

Learning from Synthetic Data: Addressing Domain Shift for Semantic Segmentation by Sankaranarayanan, Swami, Balaji, Yogesh, Jain, Arpit, Lim, Ser Nam, Chellappa, Rama

“…Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to…”
Get full text

Cross-X Learning for Fine-Grained Visual Categorization by Luo, Wei, Yang, Xitong, Mo, Xianjie, Lu, Yuheng, Davis, Larry, Li, Jun, Yang, Jian, Lim, Ser-Nam

“…Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation…”
Get full text

On Feature Normalization and Data Augmentation by Li, Boyi, Wu, Felix, Lim, Ser-Nam, Belongie, Serge, Weinberger, Kilian Q.

“…The moments (a.k.a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability…”
Get full text

ObjectFormer for Image Manipulation Detection and Localization by Wang, Junke, Wu, Zuxuan, Chen, Jingjing, Han, Xintong, Shrivastava, Abhinav, Lim, Ser-Nam, Jiang, Yu-Gang

“…Recent advances in image editing techniques have posed serious challenges to the trustworthiness of multimedia data, which drives the research of image…”
Get full text

One-Shot Domain Adaptation for Face Generation by Yang, Chao, Lim, Ser-Nam

“…In this paper, we propose a framework capable of generating face images that fall into the same distribution as that of a given one-shot example. We leverage a…”
Get full text

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition by Meng, Lingchen, Li, Hengduo, Chen, Bor-Chun, Lan, Shiyi, Wu, Zuxuan, Jiang, Yu-Gang, Lim, Ser-Nam

“…Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of tasks recently. While achieving…”
Get full text

Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation by Yang, Luyu, Wang, Yan, Gao, Mingfei, Shrivastava, Abhinav, Weinberger, Kilian Q., Chao, Wei-Lun, Lim, Ser-Nam

“…Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which…”
Get full text

Robustness and Generalization via Generative Adversarial Training by Poursaeed, Omid, Jiang, Tianxing, Yang, Harry, Belongie, Serge, Lim, Ser-Nam

“…While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle…”
Get full text

Intentonomy: a Dataset and Study towards Human Intent Understanding by Jia, Menglin, Wu, Zuxuan, Reiter, Austin, Cardie, Claire, Belongie, Serge, Lim, Ser-Nam

“…An image is worth a thousand words, conveying information that goes beyond the mere visual content therein. In this paper, we study the intent behind social…”
Get full text

Adaptive RNN Tree for Large-Scale Human Action Recognition by Wenbo Li, Longyin Wen, Ming-Ching Chang, Ser Nam Lim, Siwei Lyu

“…In this work, we present the RNN Tree (RNN-T), an adaptive learning framework for skeleton based human action recognition. Our method categorizes action…”
Get full text

Analyzing and Mitigating JPEG Compression Defects in Deep Learning by Ehrlich, Max, Davis, Larry, Lim, Ser-Nam, Shrivastava, Abhinav

“…With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One…”
Get full text

HNeRV: A Hybrid Neural Representation for Videos by Chen, Hao, Gwilliam, Matthew, Lim, Ser-Nam, Shrivastava, Abhinav

“…Implicit neural representations store videos as neural networks and have performed well for various vision tasks such as video compression and denoising. With…”
Get full text

Exploring Visual Engagement Signals for Representation Learning by Jia, Menglin, Wu, Zuxuan, Reiter, Austin, Cardie, Claire, Belongie, Serge, Lim, Ser-Nam

“…Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes. In this paper, we leverage such…”
Get full text

A Reinforcement Learning Approach to the View Planning Problem by Kaba, Mustafa Devrim, Uzunbas, Mustafa Gokhan, Ser Nam Lim

“…We present a Reinforcement Learning (RL) solution to the view planning problem (VPP), which generates a sequence of view points that are capable of sensing all…”
Get full text

Automatic Registration of Smooth Object Image to 3D CAD Model for Industrial Inspection Applications by Ser Nam Lim, Li Guan, Shubao Liu, Xingwei Yang

“…We describe an algorithmic pipeline for automatic registration of smooth object image on 3D CAD model, which has many applications in industrial inspections…”
Get full text

Towards Scalable Neural Representation for Diverse Videos by He, Bo, Yang, Xitong, Wang, Hanyu, Wu, Zuxuan, Chen, Hao, Huang, Shuaiyi, Ren, Yixuan, Lim, Ser-Nam, Shrivastava, Abhinav

“…Implicit neural representations (INR) have gained increasing attention in representing 3D scenes and images, and have been recently applied to encode videos…”
Get full text