Current methods for low- and few-shot object detection have primarily focused on enhancing model performance for detecting objects. One common approach to achieve this is by combining model finetuning with data augmentation strategies. However, little attention has been given to the energy efficiency of these approaches in data-scarce regimes. This paper seeks to conduct a comprehensive empirical study that examines both model performance and energy efficiency of custom data augmentations and automated data augmentation selection strategies when combined with a lightweight object detector. The methods are evaluated in three different benchmark datasets in terms of their performance and energy consumption, and the Efficiency Factor is employed to gain insights into their effectiveness considering both performance and efficiency. Consequently, it is shown that in many cases, the performance gains of data augmentation strategies are overshadowed by their increased energy usage, necessitating the development of more energy efficient data augmentation strategies to address data scarcity.
Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look
Shenzhen Institute of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Sangfor Technologies Inc.（深信服科技股份有限公司）
Volkswagen AG（大众汽车公司）；Technische Universität Braunschweig（布伦瑞克工业大学）
Deep neural networks are often not robust to semantically-irrelevant changes in the input. In this work we address the issue of robustness of state-of-the-art deep convolutional neural networks (CNNs) against commonly occurring distortions in the input such as photometric changes, or the addition of blur and noise. These changes in the input are often accounted for during training in the form of data augmentation. We have two major contributions: First, we propose a new regularization loss called feature-map augmentation (FMA) loss which can be used during finetuning to make a model robust to …
Multimedia Systems Department Gdańsk University of Technology（格但斯克工业大学多媒体系统系）；Gdańsk University of Technology（格但斯克工业大学）；Electronics, Telecommunications and Informatics Faculty, Gdańsk University of Technology（格但斯克工业大学电子、电信与信息学院）
While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It…
Large-scale pretraining is fast becoming the norm in Vision-Language (VL) modeling. However, prevailing VL approaches are limited by the requirement for labeled data and the use of complex multi-step pretraining objectives. We present MAGMA - a simple method for augmenting generative language models with additional modalities using adapter-based finetuning. Building on Frozen, we train a series of VL models that autoregressively generate text from arbitrary combinations of visual and textual input. The pretraining is entirely end-to-end using a single language modeling objective, simplifying o…
Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；University of Science and Technology of China（中国科学技术大学）
University of Western Ontario（西安大略大学）；University of Waterloo（滑铁卢大学）
CNNs have made a tremendous impact on the field of computer vision in the last several years. The main component of any CNN architecture is the convolution operation, which is translation invariant by design. However, location in itself can be an important cue. For example, a salient object is more likely to be closer to the center of the image, the sky in the top part of an image, etc. To include the location cue for feature learning, we propose to augment the color image, the usual input to CNNs, with one or more channels that carry location information. We test two approaches for adding loc…
Recent work indicates that, besides being a challenge in producing perceptually pleasing images, low light proves more difficult for machine cognition than previously thought. In our work, we take a closer look at object detection in low light. First, to support the development and evaluation of new methods in this domain, we present a high-quality large-scale Night Object Detection (NOD) dataset showing dynamic scenes captured on the streets at night. Next, we directly link the lighting conditions to perceptual difficulty and identify what makes low light problematic for machine cognition. Ac…
Politecnico di Torino（都灵理工大学）；Italian Institute of Technology（意大利理工学院）；MPI for Informatics（马克斯·普朗克信息学研究所）；University of Tübingen（蒂宾根大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models. However, they are prone to overfitting on the seen classes because there is no training signal for them. In this paper, we study the challenging generalized zero-label semantic segmentation task where the model has to segment both seen and unseen classes at t…
University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Research Asia（微软亚洲研究院）
Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image g…
Polytechnique Montreal（蒙特利尔理工学院）；Universite de Montreal（蒙特利尔大学）；MILA（蒙特利尔学习算法研究所）
The goal of vision-language modeling is to allow models to tie language understanding with visual inputs. The aim of this paper is to evaluate and align the Visual Language Model (VLM) called Multimodal Augmentation of Generative Models through Adapter-based finetuning (MAGMA) with human values. MAGMA is a VLM that is capable of image captioning and visual question-answering. We will evaluate its alignment in three different scenarios. To begin, we assess MAGMA's out-of-the-box alignment through the checkpoint provided by Hugging Face. Then, we measure if few-shot learning manages to improve t…
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. Our results show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets. Second, given the generality of the approach, we try to realize further gains with minor…
INESC-ID（葡萄牙国家系统与计算机工程研究所）；Instituto Superior Técnico（高等技术学院）；University of Lisbon（里斯本大学）；University of Copenhagen（哥本哈根大学）；Pioneer Center for AI（先锋人工智能中心）
Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption conditioned on an input image and related captions retrieved from a datastore. Our model is lightweight and fast to train, as the only learned parameters are in newly introduced cross-attention layers between a pre-trained CLIP encoder and GPT-2 decoder. SmallCap can transfer to new domains without additional finetuning and can exploit large-scale data in a trainin…
VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
Nanjing University（南京大学）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；Tsinghua University（清华大学）；Panasonic（松下电器（Panasonic））；University of California Berkeley（加州大学伯克利分校）
Deep Learning has thrived on the emergence of biomedical big data. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors such as operation policies, machine protocols, treatment preference and etc. As the result, models trained on one dataset, regardless of volume, cannot be confidently utilized for the others. In this study, we investigated model robustness to dataset bias using three large-scale Chest X-ray datasets: first, we assessed the dataset bias using vanilla training baseline; second, we proposed a novel multi-source dom…
Linköping University（林雪平大学）；Sectra AB（斯凯特拉公司）；Center for Medical Image Science and Visualization（医学影像科学与可视化中心）
Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images. We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to. Most centrally, we present a novel measure fo…
FACT: A Simple and Efficient Framework for Active Finetuning
Zhejiang (No. 2024C01020)（浙江（No. 2024C01020））；National Natural Science Foundation of China (No. 62302031)（中国国家自然科学基金委员会（No. 62302031））；Zhejiang Provincial Natural Science Foundation of China (Nos. LQ23F020024 and LZJMZ24D050009)（中国浙江省自然科学基金委员会（Nos. LQ23F020024 and LZJMZ24D050009））
We present a new approach to the problem of estimating the 3D room layout from a single panoramic image. We represent room layout as three 1D vectors that encode, at each image column, the boundary positions of floor-wall and ceiling-wall, and the existence of wall-wall boundary. The proposed network, HorizonNet, trained for predicting 1D layout, outperforms previous state-of-the-art approaches. The designed post-processing procedure for recovering 3D room layouts from 1D predictions can automatically infer the room shape with low computation cost - it takes less than 20ms for a panorama image…
Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning. By substituting simple noising operations with advanced data augmentati…
University of Electronic Science and Technology of China（电子科技大学）；University of Toronto（多伦多大学）；The Hospital for Sick Children (SickKids)（SickKids 儿童医院（病童医院））；Sinai Health System（西奈卫生系统）；University Health Network（大学健康网络）；Lunenfeld-Tanenbaum Research Institute（卢嫩菲尔德-塔南鲍姆研究所）；Sunnybrook Research Institute（桑尼布鲁克研究所）
Data augmentation refers to a group of techniques whose goal is to battle limited amount of available data to improve model generalization and push sample distribution toward the true distribution. While different augmentation strategies and their combinations have been investigated for various computer vision tasks in the context of deep learning, a specific work in the domain of medical imaging is rare and to the best of our knowledge, there has been no dedicated work on exploring the effects of various augmentation methods on the performance of deep learning models in prostate cancer detect…
Planet AI GmbH（Planet AI公司）；University of Würzburg（维尔茨堡大学）；Rostock University（罗斯托克大学）；LMU Munich（慕尼黑大学）
In order to apply Optical Character Recognition (OCR) to historical printings of Latin script fully automatically, we report on our efforts to construct a widely-applicable polyfont recognition model yielding text with a Character Error Rate (CER) around 2% when applied out-of-the-box. Moreover, we show how this model can be further finetuned to specific classes of printings with little manual and computational effort. The mixed or polyfont model is trained on a wide variety of materials, in terms of age (from the 15th to the 19th century), typography (various types of Fraktur and Antiqua), an…
Are nuclear masks all you need for improved out-of-domain generalisation? A closer look at cancer classification in histopathology
University of Oslo（奥斯陆大学）；Otto-von-Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）；Singapore Institute of Technology（新加坡科技学院）；Oslo University Hospital（奥斯陆大学医院）；UiT The Arctic University of Norway（挪威北极大学）
CLIP-Guided Data Augmentation for Night-Time Image Dehazing
Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（济南大学）；Hefei University of Technology（合肥工业大学）；Wuhan University（武汉大学）；The University of Tokyo（东京大学）
Inspur Electronic Information Industry Co., Ltd（浪潮电子信息产业股份有限公司）；Shandong Massive Information Technology Research Institute（山东海量信息技术研究院）
Although deep learning has significantly improved Face Recognition (FR), dramatic performance deterioration may occur when processing Low Resolution (LR) faces. To alleviate this, approaches based on unified feature space are proposed with the sacrifice under High Resolution (HR) circumstances. To deal with the huge domain gap between HR and LR domains and achieve the best on both domains, we first took a closer look at the impacts of several resolution augmentations and then analyzed the difficulty of LR samples from the perspective of the model gradient produced by different resolution sampl…
EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学现代软件技术国家重点实验室）；Department of Computer Science and Technology, Nanjing University（南京大学计算机科学与技术系）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）
本文提出无需调参的自适应数据增强框架 EntAugment，依据模型 softmax 输出的信息熵逐样本调整增强幅度，并结合 EntLoss 正则化，在图像分类中以低额外成本取得优于现有 DA 方法的性能。
Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive Evaluation
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
SINTEF（挪威科学与工业研究基金会）；Norwegian University of Science and Technology (NTNU)（挪威科技大学）；St. Olavs hospital, Trondheim University Hospital（圣奥拉夫医院，特隆赫姆大学医院）；Oslo University Hospital（奥斯陆大学医院）
Purpose: This study aims to explore training strategies to improve convolutional neural network-based image-to-image deformable registration for abdominal imaging. Methods: Different training strategies, loss functions, and transfer learning schemes were considered. Furthermore, an augmentation layer which generates artificial training image pairs on-the-fly was proposed, in addition to a loss layer that enables dynamic loss weighting. Results: Guiding registration using segmentations in the training step proved beneficial for deep-learning-based image registration. Finetuning the pretrained m…
