Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAre Labels Always Necessary for Classifier Accuracy Evaluation?
104
0
0.0
(
0
)
Added by
Deng Weijian
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
To calculate the model accuracy on a computer vision task, e.g., object recognition, we usually require a test set composing of test samples and their ground truth labels. Whilst standard usage cases satisfy this requirement, many real-world scenarios involve unlabeled test data, rendering common model evaluation methods infeasible. We investigate this important and under-explored problem, Automatic model Evaluation (AutoEval). Specifically, given a labeled training set and a classifier, we aim to estimate the classification accuracy on unlabeled test datasets. We construct a meta-dataset: a dataset comprised of datasets generated from the original images via various transformations such as rotation, background substitution, foreground scaling, etc. As the classification accuracy of the model on each sample (dataset) is known from the original dataset labels, our task can be solved via regression. Using the feature statistics to represent the distribution of a sample dataset, we can train regression models (e.g., a regression neural network) to predict model performance. Using synthetic meta-dataset and real-world datasets in training and testing, respectively, we report a reasonable and promising prediction of the model accuracy. We also provide insights into the application scope, limitation, and potential future direction of AutoEval.
rate research
Read More
Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels. In this paper, we ask the question: can we find high-quality neural architectures using only images, but no human-annotated labels? To answer this question, we first define a new setup called Unsupervised Neural Architecture Search (UnNAS). We then conduct two sets of experiments. In sample-based experiments, we train a large number (500) of diverse architectures with either supervised or unsupervised objectives, and find that the architecture rankings produced with and without labels are highly correlated. In search-based experiments, we run a well-established NAS algorithm (DARTS) using various unsupervised objectives, and report that the architectures searched without labels can be competitive to their counterparts searched with labels. Together, these results reveal the potentially surprising finding that labels are not necessary, and the image statistics alone may be sufficient to identify good neural architectures.
In many classification tasks, the ground truth is either noisy or subjective. Examples include: which of two alternative paper titles is better? is this comment toxic? what is the political leaning of this news article? We refer to such tasks as survey settings because the ground truth is defined through a survey of one or more human raters. In survey settings, conventional measurements of classifier accuracy such as precision, recall, and cross-entropy confound the quality of the classifier with the level of agreement among human raters. Thus, they have no meaningful interpretation on their own. We describe a procedure that, given a dataset with predictions from a classifier and K ratings per item, rescales any accuracy measure into one that has an intuitive interpretation. The key insight is to score the classifier not against the best proxy for the ground truth, such as a majority vote of the raters, but against a single human rater at a time. That score can be compared to other predictors scores, in particular predictors created by combining labels from several other human raters. The survey equivalence of any classifier is the minimum number of raters needed to produce the same expected score as that found for the classifier.
Few-shot learning is challenging due to its very limited data and labels. Recent studies in big transfer (BiT) show that few-shot learning can greatly benefit from pretraining on large scale labeled dataset in a different domain. This paper asks a more challenging question: can we use as few as possible labels for few-shot learning in both pretraining (with no labels) and fine-tuning (with fewer labels)?. Our key insight is that the clustering of target samples in the feature space is all we need for few-shot finetuning. It explains why the vanilla unsupervised pretraining (poor clustering) is worse than the supervised one. In this paper, we propose transductive unsupervised pretraining that achieves a better clustering by involving target data even though its amount is very limited. The improved clustering result is of great value for identifying the most representative samples (eigen-samples) for users to label, and in return, continued finetuning with the labeled eigen-samples further improves the clustering. Thus, we propose eigen-finetuning to enable fewer shot learning by leveraging the co-evolution of clustering and eigen-samples in the finetuning. We conduct experiments on 10 different few-shot target datasets, and our average few-shot performance outperforms both vanilla inductive unsupervised transfer and supervised transfer by a large margin. For instance, when each target category only has 10 labeled samples, the mean accuracy gain over the above two baselines is 9.2% and 3.42 respectively.
Adversarial training (AT) based on minimax optimization is a popular learning style that enhances the models adversarial robustness. Noisy labels (NL) commonly undermine the learning and hurt the models performance. Interestingly, both research directions hardly crossover and hit sparks. In this paper, we raise an intriguing question -- Does NL always hurt AT? Firstly, we find that NL injection in inner maximization for generating adversarial data augments natural data implicitly, which benefits ATs generalization. Secondly, we find NL injection in outer minimization for the learning serves as regularization that alleviates robust overfitting, which benefits ATs robustness. To enhance ATs adversarial robustness, we propose NoiLIn that gradually increases underline{Noi}sy underline{L}abels underline{In}jection over the ATs training process. Empirically, NoiLIn answers the previous question negatively -- the adversarial robustness can be indeed enhanced by NL injection. Philosophically, we provide a new perspective of the learning with NL: NL should not always be deemed detrimental, and even in the absence of NL in the training set, we may consider injecting it deliberately.
The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. As a result, an in-depth evaluation among different object detection methods remains challenging, and the training process of object detectors is sub-optimal, especially in probabilistic object detection. In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model, and define a new representation of the probabilistic bounding box through a spatial uncertainty distribution. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. Furthermore, we propose Jaccard IoU (JIoU) as a new evaluation metric that extends IoU by incorporating label uncertainty. We conduct an in-depth comparison among several LiDAR-based object detectors using the JIoU metric. Finally, we incorporate the proposed label uncertainty in a loss function to train a probabilistic object detector and to improve its detection accuracy. We verify our proposed methods on two public datasets (KITTI, Waymo), as well as on simulation data. Code is released at https://bit.ly/2W534yo.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
