Author name cluster

Jun Hou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

AAAI Conference 2025 Conference Paper

SceneX: Procedural Controllable Large-Scale Scene Generation

Mengqi Zhou
Yuxi Wang
Jun Hou
Shougao Zhang
Yiwei Li
Chuanchen Luo
Junran Peng
Zhaoxiang Zhang

Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural Controllable Generation (PCG) has gained significant attention in large-scale scene generation by enabling the creation of scalable, high-quality assets. However, PCG faces challenges such as limited modular diversity, high expertise requirements, and challenges in managing the diverse elements and structures in complex scenes. In this paper, we introduce a large-scale scene generation framework, SceneX, which can automatically produce high-quality procedural models according to designers' textual descriptions. Specifically, the proposed method comprises two components, PCGHub and PCGPlanner. The former encompasses an extensive collection of accessible procedural assets and thousands of hand-craft API documents to perform as a standard protocol for PCG controller. The latter aims to generate executable actions for Blender to produce controllable and precise 3D assets guided by the user's instructions. Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

Sikai Bai
Shuaicheng Li
Weiming Zhuang
Jie Zhang
Kunlin Yang
Jun Hou
Shuai Yi
Shuai Zhang

Federated learning has become a popular method to learn from decentralized heterogeneous data. Federated semi-supervised learning (FSSL) emerges to train models from a small fraction of labeled data due to label scarcity on decentralized clients. Existing FSSL methods assume independent and identically distributed (IID) labeled data across clients and consistent class distribution between labeled and unlabeled data within a client. This work studies a more practical and challenging scenario of FSSL, where data distribution is different not only across clients but also within a client between labeled and unlabeled data. To address this challenge, we propose a novel FSSL framework with dual regulators, FedDure. FedDure lifts the previous assumption with a coarse-grained regulator (C-reg) and a fine-grained regulator (F-reg): C-reg regularizes the updating of the local model by tracking the learning effect on labeled data distribution; F-reg learns an adaptive weighting scheme tailored for unlabeled instances in each client. We further formulate the client model training as bi-level optimization that adaptively optimizes the model in the client with two regulators. Theoretically, we show the convergence guarantee of the dual regulators. Empirically, we demonstrate that FedDure is superior to the existing methods across a wide range of settings, notably by more than 11% on CIFAR-10 and CINIC-10 datasets.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation

Martin Zong
Zengyu Qiu
Xinzhu Ma
Kunlin Yang
Chunya Liu
Jun Hou
Shuai Yi
Wanli Ouyang

Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger, existing KD methods fail to achieve better results. Our work shows that the 'prior knowledge' is vital to KD, especially when applying large teachers. Particularly, we propose the dynamic prior knowledge (DPK), which integrates part of teacher's features as the prior knowledge before the feature distillation. This means that our method also takes the teacher's feature as `input', not just `target'. Besides, we dynamically adjust the ratio of the prior knowledge during the training phase according to the feature gap, thus guiding the student in an appropriate difficulty. To evaluate the proposed method, we conduct extensive experiments on two image classification benchmarks (i.e. CIFAR100 and ImageNet) and an object detection benchmark (\i.e. MS COCO). The results demonstrate the superiority of our method in performance under varying settings. Besides, our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers. More importantly, DPK provides a fast solution in teacher model selection for any given model. Our codes will be publicly available for reproducibility.

Details

EAAI Journal 2023 Journal Article

Underwater self-supervised monocular depth estimation and its application in image enhancement

Junting Wang
Xiufen Ye
Yusong Liu
Xinkui Mei
Jun Hou

Accurate depth estimation is necessary for imaging model-based underwater image enhancement. However, limited by the length of baseline, traditional binocular-based methods are not easy to deploy in underwater scenarios, while monocular methods are more appropriate due to their availability and cost. Therefore, we propose a self-supervised model (called UWdepth) to estimate the depth of underwater scenes with monocular sequences. Addressing the challenges posed by the scale of data and the complexity of motion in underwater scenes, we design an iterative pose network and further introduce a depth consistency loss to achieve more accurate inter-frame motion prediction and depth estimation. The predicted depth can be used to precisely enhance the image based on the underwater imaging model. Experiments show that UWdepth outperforms existing depth estimation models in terms of multiple evaluation indexes. Furthermore, by applying UWdepth, we can enhance underwater images with Akkaynak–Treibitz imaging model, achieving better indexes and visual perception quality than existing traditional and deep-learning based underwater image enhancement algorithms.

Details DOI

AAAI Conference 2022 Conference Paper

Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention

Kun Yan
Chenbin Zhang
Jun Hou
Ping Wang
Zied Bouraoui
Shoaib Jameel
Steven Schockaert

Multi-label few-shot image classification (ML-FSIC) is the task of assigning descriptive labels to previously unseen images, based on a small number of training examples. A key feature of the multi-label setting is that images often have multiple labels, which typically refer to different regions of the image. When estimating prototypes, in a metric-based setting, it is thus important to determine which regions are relevant for which labels, but the limited amount of training data makes this highly challenging. As a solution, in this paper, we propose to use word embeddings as a form of prior knowledge about the meaning of the labels. In particular, visual prototypes are obtained by aggregating the local feature maps of the support images, using an attention mechanism that relies on the label embeddings. As an important advantage, our model can infer prototypes for unseen labels without the need for fine-tuning any model parameters, which demonstrates its strong generalization abilities. Experiments on COCO and PASCAL VOC furthermore show that our model substantially improves the current state-of-the-art.

PDF Details

AAAI Conference 2020 Conference Paper

GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition

Wenyang Hu
Xiaocong Cai
Jun Hou
Shuai Yi
Zhiping Lin

Connectionist Temporal Classiﬁcation (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efﬁcient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the bene- ﬁt of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast inference speed. Moreover, to further leverage the potential of CTC decoder, a graph convolutional network (GCN) is proposed to learn the local correlations of extracted features. Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attentionbased methods.

PDF Details