15 citations · 57 across the 21 of their papers we have counts for
23 papers
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Lei Zhang, Junjiao Tian, Zhipeng Fan +9
Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual…
Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models
Xu Ma, Peize Sun, Haoyu Ma +22
Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models.…
Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
Chengyue Huang, Junjiao Tian, Brisa Maneechotesuwan +2
Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constrain…
Grounding Descriptions in Images informs Zero-Shot Visual Recognition
Shaunak Halbe, Junjiao Tian, K J Joseph +4
Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the…
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
Junjiao Tian, Chengyue Huang, Zsolt Kira
Modern optimizers such as AdamW, equipped with momentum and adaptive learning rate, are designed to escape local minima and explore the vast parameter space. This exploration is be…
Fast Trainable Projection for Robust Fine-Tuning
Junjiao Tian, Yen-Cheng Liu, James Seale Smith +1
Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring…
Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
Junjiao Tian, Lavisha Aggarwal, Andrea Colaco +2
Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmen…
Continual Adaptation of Vision Transformers for Federated Learning
Shaunak Halbe, James Seale Smith, Junjiao Tian +1
In this paper, we focus on the important yet understudied problem of Continual Federated Learning (CFL), where a server communicates with a set of clients to incrementally learn ne…
Trainable Projected Gradient Method for Robust Fine-tuning
Junjiao Tian, Xiaoliang Dai, Chih-Yao Ma +3
Recent studies on transfer learning have shown that selectively fine-tuning a subset of layers or customizing different learning rates for each layer can greatly improve robustness…
Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks
Yen-Cheng Liu, Chih-Yao Ma, Junjiao Tian +2
Adapting large-scale pretrained models to various downstream tasks via fine-tuning is a standard method in machine learning. Recently, parameter-efficient fine-tuning methods show…
FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization
Junjiao Tian, James Seale Smith, Zsolt Kira
Federated Learning (FL) seeks to distribute model training across local clients without collecting data in a centralized data-center, hence removing data-privacy concerns. A major…
Open-Set Semi-Supervised Object Detection
Yen-Cheng Liu, Chih-Yao Ma, Xiaoliang Dai +4
Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods h…
A Closer Look at Rehearsal-Free Continual Learning
James Seale Smith, Junjiao Tian, Shaunak Halbe +2
Continual learning is a setting where machine learning models learn novel concepts from continuously shifting training data, while simultaneously avoiding degradation of knowledge…
Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data
Junjiao Tian, Yen-Change Hsu, Yilin Shen +2
Moving beyond testing on in-distribution data works on Out-of-Distribution (OOD) detection have recently increased in popularity. A recent attempt to categorize OOD data introduces…
A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition
Junjiao Tian, Dylan Yung, Yen-Chang Hsu +1
It is well known that vision classification models suffer from poor calibration in the face of data distribution shifts. In this paper, we take a geometric approach to this problem…
Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking
Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian +1
In this paper, we address bandwidth-limited and obstruction-prone collaborative perception, specifically in the context of multi-agent semantic segmentation. This setting presents…
Enhancing Multi-Robot Perception via Learned Data Association
Nathaniel Glaser, Yen-Cheng Liu, Junjiao Tian +1
In this paper, we address the multi-robot collaborative perception problem, specifically in the context of multi-view infilling for distributed semantic segmentation. This setting…
Striking the Right Balance: Recall Loss for Semantic Segmentation
Junjiao Tian, Niluthpol Mithun, Zach Seymour +2
Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result…
Posterior Re-calibration for Imbalanced Datasets
Junjiao Tian, Yen-Cheng Liu, Nathan Glaser +2
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. In order to…
Image Captioning with Compositional Neural Module Networks
Junjiao Tian, Jean Oh
In image captioning where fluency is an important factor in evaluation, e.g., -gram metrics, sequential models are commonly used; however, sequential models generally result in…
When2com: Multi-Agent Perception via Communication Graph Grouping
Yen-Cheng Liu, Junjiao Tian, Nathaniel Glaser +1
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 cover…
Who2com: Collaborative Perception via Learnable Handshake Communication
Yen-Cheng Liu, Junjiao Tian, Chih-Yao Ma +3
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…
UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation
Junjiao Tian, Wesley Cheung, Nathan Glaser +2
The fusion of multiple sensor modalities, especially through deep learning architectures, has been an active area of study. However, an under-explored aspect of such work is whethe…