1 code implementation • 23 Aug 2023 • Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, Mar Gonzalez-Franco
The proposed method does not require any training or language dependency to extract quality segmentation for any images.
Ranked #1 on Semantic Segmentation on COCO-Stuff-27
no code implementations • 16 Jun 2023 • Shaunak Halbe, James Seale Smith, Junjiao Tian, Zsolt Kira
In this paper, we attempt to tackle forgetting and heterogeneity while minimizing overhead costs and without requiring access to any stored data.
2 code implementations • CVPR 2023 • Junjiao Tian, Xiaoliang Dai, Chih-Yao Ma, Zecheng He, Yen-Cheng Liu, Zsolt Kira
To solve this problem, we propose Trainable Projected Gradient Method (TPGM) to automatically learn the constraint imposed for each layer for a fine-grained fine-tuning regularization.
no code implementations • 7 Oct 2022 • Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian, Zijian He, Zsolt Kira
Specifically, Polyhistor achieves competitive accuracy compared to the state-of-the-art while only using ~10% of their trainable parameters.
1 code implementation • 21 Sep 2022 • Junjiao Tian, James Seale Smith, Zsolt Kira
For the more typical applications of FL where the number of clients is large (e. g., edge-device and mobile applications), these methods cannot be applied, motivating the need for a stateless approach to heterogeneous FL which can be used for any number of clients.
no code implementations • 29 Aug 2022 • Yen-Cheng Liu, Chih-Yao Ma, Xiaoliang Dai, Junjiao Tian, Peter Vajda, Zijian He, Zsolt Kira
To address this problem, we consider online and offline OOD detection modules, which are integrated with SSOD methods.
no code implementations • 31 Mar 2022 • James Seale Smith, Junjiao Tian, Shaunak Halbe, Yen-Chang Hsu, Zsolt Kira
Next, we explore how to leverage knowledge from a pre-trained model in rehearsal-free continual learning and find that vanilla L2 parameter regularization outperforms EWC parameter regularization and feature distillation.
no code implementations • 28 Oct 2021 • Junjiao Tian, Yen-Change Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira
We are the first to propose a method that works well across both OOD detection and calibration and under different types of shifts.
1 code implementation • NeurIPS 2021 • Junjiao Tian, Dylan Yung, Yen-Chang Hsu, Zsolt Kira
It is well known that vision classification models suffer from poor calibration in the face of data distribution shifts.
no code implementations • 29 Sep 2021 • Junjiao Tian, Yen-Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira
To this end, we theoretically derive two score functions for OOD detection, the covariate shift score and concept shift score, based on the decomposition of KL-divergence for both scores, and propose a geometrically-inspired method (Geometric ODIN) to improve OOD detection under both shifts with only in-distribution data.
no code implementations • 1 Jul 2021 • Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian, Zsolt Kira
In this paper, we address the multi-robot collaborative perception problem, specifically in the context of multi-view infilling for distributed semantic segmentation.
no code implementations • 1 Jul 2021 • Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian, Zsolt Kira
In this paper, we address bandwidth-limited and obstruction-prone collaborative perception, specifically in the context of multi-agent semantic segmentation.
1 code implementation • 28 Jun 2021 • Junjiao Tian, Niluthpol Mithun, Zach Seymour, Han-Pang Chiu, Zsolt Kira
There are two major drawbacks to these methods: 1) constantly up-weighting minority classes can introduce excessive false positives in semantic segmentation; 2) a minority class is not necessarily a hard class.
1 code implementation • 1 Jan 2021 • Junjiao Tian, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Zsolt Kira
Many works have proposed to weigh the standard cross entropy loss function with pre-computed weights based on class statistics such as the number of samples and class margins.
no code implementations • NeurIPS 2020 • Junjiao Tian, Yen-Cheng Liu, Nathan Glaser, Yen-Chang Hsu, Zsolt Kira
Neural Networks can perform poorly when the training label distribution is heavily imbalanced, as well as when the testing data differs from the training distribution.
Ranked #31 on Long-tail Learning on CIFAR-100-LT (ρ=10)
no code implementations • 10 Jul 2020 • Junjiao Tian, Jean Oh
In image captioning where fluency is an important factor in evaluation, e. g., $n$-gram metrics, sequential models are commonly used; however, sequential models generally result in overgeneralized expressions that lack the details that may be present in an input image.
2 code implementations • CVPR 2020 • Yen-Cheng Liu, Junjiao Tian, Nathaniel Glaser, Zsolt Kira
While significant advances have been made for single-agent perception, many applications require multiple sensing agents and cross-agent communication due to benefits such as coverage and robustness.
1 code implementation • 21 Mar 2020 • Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma, Nathan Glaser, Chia-Wen Kuo, Zsolt Kira
In this paper, we propose the problem of collaborative perception, where robots can combine their local observations with those of neighboring agents in a learnable way to improve accuracy on a perception task.
no code implementations • 6 Nov 2019 • Junjiao Tian, Wesley Cheung, Nathan Glaser, Yen-Cheng Liu, Zsolt Kira
Specifically, we analyze a number of uncertainty measures, each of which captures a different aspect of uncertainty, and we propose a novel way to fuse degraded inputs by scaling modality-specific output softmax probabilities.