37 citations · 105 across the 20 of their papers we have counts for
20 papers
A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
Xin Wen, Bingchen Zhao, Yilun Chen +2
Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear. Through systematic evaluation, we find that while DINO and iBO…
"Principal Components" Enable A New Language of Images
Xin Wen, Bingchen Zhao, Ismail Elezi +2
We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. While existing visual tokenizers primarily optimize for re…
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights
Xin Wen, Bingchen Zhao, Yilun Chen +2
Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance…
Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery
Bingchen Zhao, Xin Wen, Kai Han
In this paper, we address the problem of generalized category discovery (GCD), \ie, given a set of images where part of them are labelled and the rest are not, the task is to autom…
Incremental Generalized Category Discovery
Bingchen Zhao, Oisin Mac Aodha
We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that ca…
OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images
Bingchen Zhao, Jiahao Wang, Wufei Ma +7
Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on syntheti…
Vision Learners Meet Web Image-Text Pairs
Bingchen Zhao, Quan Cui, Hao Wu +3
Many self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervise…
One Venue, Two Conferences: The Separation of Chinese and American Citation Networks
Bingchen Zhao, Yuling Gu, Jessica Zosa Forde +1
At NeurIPS, American and Chinese institutions cite papers from each other's regions substantially less than they cite endogamously. We build a citation graph to quantify this divid…
Parametric Classification for Generalized Category Discovery: A Baseline Study
Xin Wen, Bingchen Zhao, Xiaojuan Qi
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. Previous studies argued that parametric…
XCon: Learning with Experts for Fine-grained Category Discovery
Yixin Fei, Zhongkai Zhao, Siwei Yang +1
We address the problem of generalized category discovery (GCD) in this paper, i.e. clustering the unlabeled images leveraging the information from a set of seen classes, where the…
Self-Supervised Visual Representation Learning with Semantic Grouping
Xin Wen, Bingchen Zhao, Anlin Zheng +2
In this paper, we tackle the problem of learning visual representations from unlabeled scene-centric data. Existing works have demonstrated the potential of utilizing the underlyin…
Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
Quan Cui, Bingchen Zhao, Zhao-Min Chen +5
This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i.e., image classification.…
OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images
Bingchen Zhao, Shaozuo Yu, Wufei Ma +6
Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on syntheti…
Improving Contrastive Learning by Visualizing Feature Transformation
Rui Zhu, Bingchen Zhao, Jingen Liu +2
Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised…
Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
Bingchen Zhao, Kai Han
In this paper, we tackle the problem of novel visual category discovery, i.e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labell…
Rail-5k: a Real-World Dataset for Rail Surface Defects Detection
Zihao Zhang, Shaozuo Yu, Siwei Yang +2
This paper presents the Rail-5k dataset for benchmarking the performance of visual algorithms in a real-world application scenario, namely the rail surface defects detection task.…
Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization
Siwei Yang, Shaozuo Yu, Bingchen Zhao +1
Visual pattern recognition over agricultural areas is an important application of aerial image processing. In this paper, we consider the multi-modality nature of agricultural aeri…
Temporal Context Aggregation for Video Retrieval with Contrastive Learning
Jie Shao, Xin Wen, Bingchen Zhao +1
The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events…
Distilling Visual Priors from Self-Supervised Learning
Bingchen Zhao, Xin Wen
Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge disti…
The 1st Agriculture-Vision Challenge: Methods and Results
Mang Tik Chiu, Xingqian Xu, Kai Wang +39
The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially f…