English
Related papers

Related papers: Improving Baselines in the Wild

200 papers

Pre-training has been widely adopted in deep learning to improve model performance, especially when the training data for a target task is limited. In our work, we seek to understand the implications of this training strategy on the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Vivek Ramanujan , Thao Nguyen , Sewoong Oh , Ludwig Schmidt , Ali Farhadi

Softmax-based losses have achieved state-of-the-art performances on various tasks such as face recognition and re-identification. However, these methods highly relied on clean datasets with global labels, which limits their usage in many…

Computer Vision and Pattern Recognition · Computer Science 2022-01-25 Qiang Meng , Xinqian Gu , Xiaqing Xu , Feng Zhou

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows…

Computer Vision and Pattern Recognition · Computer Science 2021-02-12 Yuhe Jin , Dmytro Mishkin , Anastasiia Mishchuk , Jiri Matas , Pascal Fua , Kwang Moo Yi , Eduard Trulls

Complex Word Identification (CWI) is the task of identifying which words or phrases in a sentence are difficult to understand by a target audience. The latest CWI Shared Task released data for two settings: monolingual (i.e. train and test…

Computation and Language · Computer Science 2019-04-15 Pierre Finnimore , Elisabeth Fritzsch , Daniel King , Alison Sneyd , Aneeq Ur Rehman , Fernando Alva-Manchego , Andreas Vlachos

Mitigating human-wildlife conflict seeks to resolve unwanted encounters between these parties. Computer Vision provides a solution to identifying individuals that might escalate into conflict, such as members of the Big Five African…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Mufhumudzi Muthivhi , Jiahao Huo , Fredrik Gustafsson , Terence L. van Zyl

Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performance under distribution shifts. Current approaches to robust…

Machine Learning · Computer Science 2024-03-15 Caroline Choi , Yoonho Lee , Annie Chen , Allan Zhou , Aditi Raghunathan , Chelsea Finn

Understanding the interplay between intra-modality dependencies (the contribution of an individual modality to a target task) and inter-modality dependencies (the relationships between modalities and the target task) is fundamental to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Divyam Madaan , Varshan Muhunthan , Kyunghyun Cho , Sumit Chopra

Tabular data is widely utilized in various machine learning tasks. Current tabular learning research predominantly focuses on closed environments, while in real-world applications, open environments are often encountered, where distribution…

Machine Learning · Computer Science 2025-06-03 Zi-Jian Cheng , Zi-Yi Jia , Zhi Zhou , Yu-Feng Li , Lan-Zhe Guo

Since the advent of controllable image generation, increasingly rich modes of control have enabled greater customization and accessibility for everyday users. Zero-shot, identity-preserving models such as Insert Anything and OminiControl…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Aaron Sun , Oindrila Saha , Subhransu Maji

Training with more data has always been the most stable and effective way of improving performance in deep learning era. As the largest object detection dataset so far, Open Images brings great opportunities and challenges for object…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Junran Peng , Xingyuan Bu , Ming Sun , Zhaoxiang Zhang , Tieniu Tan , Junjie Yan

In the current landscape of foundation model training, there is a significant reliance on public domain data, which is nearing exhaustion according to recent research. To further scale up, it is crucial to incorporate collaboration among…

Machine Learning · Computer Science 2024-03-08 Wanru Zhao , Yaxin Du , Nicholas Donald Lane , Siheng Chen , Yanfeng Wang

Animal Re-ID has recently gained substantial attention in the AI research community due to its high impact on biodiversity monitoring and unique research challenges arising from environmental factors. The subtle distinguishing patterns,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Depanshu Sani , Mehar Khurana , Saket Anand

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Zhenda Xie , Zheng Zhang , Yue Cao , Yutong Lin , Yixuan Wei , Qi Dai , Han Hu

Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Nikita Kisel , Illia Volkov , Katerina Hanzelkova , Klara Janouskova , Jiri Matas

The quality and generality of deep image features is crucially determined by the data they have been trained on, but little is known about this often overlooked effect. In this paper, we systematically study the effect of variations in the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Othman Sbai , Camille Couprie , Mathieu Aubry

Multimodal fusion is a significant method for most multimodal tasks. With the recent surge in the number of large pre-trained models, combining both multimodal fusion methods and pre-trained model features can achieve outstanding…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Zhuofan Wen , Fengyu Zhang , Siyuan Zhang , Haiyang Sun , Mingyu Xu , Licai Sun , Zheng Lian , Bin Liu , Jianhua Tao

Vision-language models (VLMs) excel at broad visual understanding but remain coarse-grained, exhibit visual biases, and miss subtle visual details. Existing training corpora reinforce this limitation by emphasizing general recognition ("Is…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Damiano Marsili , Aditya Mehta , Ryan Y. Lin , Georgia Gkioxari

Intrinsic image decomposition and inverse rendering are long-standing problems in computer vision. To evaluate albedo recovery, most algorithms report their quantitative performance with a mean Weighted Human Disagreement Rate (WHDR) metric…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Jiaye Wu , Sanjoy Chowdhury , Hariharmano Shanmugaraja , David Jacobs , Soumyadip Sengupta

Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying rules that govern environment dynamics. In this work, we address this open…

Machine Learning · Computer Science 2025-12-01 Xinyi Li , Zaishuo Xia , Weyl Lu , Chenjie Hao , Yubei Chen

Robustness to natural distribution shifts has seen remarkable progress thanks to recent pre-training strategies combined with better fine-tuning methods. However, such fine-tuning assumes access to large amounts of labelled data, and the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Aaditya Singh , Kartik Sarangmath , Prithvijit Chattopadhyay , Judy Hoffman