185 citations · 326 across the 41 of their papers we have counts for
14 papers · 1 filter
Universal Pyramid Adversarial Training for Improved ViT Performance
Ping-yeh Chiang, Yipin Zhou, Omid Poursaeed +4
Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very effective for improving clean accuracy and distribution-shift robustness of vision transfor…
From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim +3
Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a…
Language-free Compositional Action Generation via Decoupling Refinement
Xiao Liu, Guangyi Chen, Yansong Tang +3
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation. Existing methods largely rely on extensive neural language annotati…
Graph Inductive Biases in Transformers without Message Passing
Liheng Ma, Chen Lin, Derek Lim +5
Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works…
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim +3
We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the mode…
HNeRV: A Hybrid Neural Representation for Videos
Hao Chen, Matt Gwilliam, Ser-Nam Lim +1
Implicit neural representations store videos as neural networks and have performed well for various vision tasks such as video compression and denoising. With frame index or positi…
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
Zhuoling Li, Chuanrui Zhang, Wei-Chiu Ma +5
In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks. However, their performance in multi-view 3D object detection re…
LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision
Jiani Huang, Ziyang Li, Mayur Naik +1
Supervised approaches for learning spatio-temporal scene graphs (STSG) from video are greatly hindered due to their reliance on STSG-annotated videos, which are labor-intensive to…
Detecting Everything in the Open World: Towards Universal Object Detection
Zhenyu Wang, Yali Li, Xi Chen +4
In this paper, we formally address universal object detection, which aims to detect every scene and predict every category. The dependence on human annotations, the limited visual…
ScribbleSeg: Scribble-based Interactive Image Segmentation
Xi Chen, Yau Shing Jonathan Cheung, Ser-Nam Lim +1
Interactive segmentation enables users to extract masks by providing simple annotations to indicate the target, such as boxes, clicks, or scribbles. Among these interaction formats…
Open-vocabulary Panoptic Segmentation with Embedding Modulation
Xi Chen, Shuang Li, Ser-Nam Lim +2
Open-vocabulary image segmentation is attracting increasing attention due to its critical applications in the real world. Traditional closed-vocabulary segmentation methods are not…
Computationally Budgeted Continual Learning: What Does Matter?
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet Dokania +4
Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current…
Test-Time Distribution Normalization for Contrastively Learned Vision-language Models
Yifei Zhou, Juntao Ren, Fengyu Li +2
Advances in the field of vision-language contrastive learning have made it possible for many downstream applications to be carried out efficiently and accurately by simply taking t…
Metric Compatible Training for Online Backfilling in Large-Scale Retrieval
Seonguk Seo, Mustafa Gokhan Uzunbas, Bohyung Han +2
Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computati…