@inproceedings{14771, abstract = {Pruning—that is, setting a significant subset of the parameters of a neural network to zero—is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate bias in the output of the compressed model. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood. In this work, we systematically investigate and characterize this phenomenon in Convolutional Neural Networks for computer vision. First, we show that it is in fact possible to obtain highly-sparse models, e.g. with less than 10% remaining weights, which do not decrease in accuracy nor substantially increase in bias when compared to dense models. At the same time, we also find that, at higher sparsities, pruned models exhibit higher uncertainty in their outputs, as well as increased correlations, which we directly link to increased bias. We propose easy-to-use criteria which, based only on the uncompressed model, establish whether bias will increase with pruning, and identify the samples most susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias.}, author = {Iofinova, Eugenia B and Peste, Elena-Alexandra and Alistarh, Dan-Adrian}, booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {Vancouver, BC, Canada}, pages = {24364--24373}, publisher = {IEEE}, title = {{Bias in pruned vision models: In-depth analysis and countermeasures}}, doi = {10.1109/cvpr52729.2023.02334}, year = {2023}, } @inproceedings{12299, abstract = {Transfer learning is a classic paradigm by which models pretrained on large “upstream” datasets are adapted to yield good results on “downstream” specialized datasets. Generally, more accurate models on the “upstream” dataset tend to provide better transfer accuracy “downstream”. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset, which have been pruned-that is, compressed by sparsifiying their connections. We consider transfer using unstructured pruned models obtained by applying several state-of-the-art pruning methods, including magnitude-based, second-order, regrowth, lottery-ticket, and regularization approaches, in the context of twelve standard transfer tasks. In a nutshell, our study shows that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities, and, while doing so, can lead to significant inference and even training speedups. At the same time, we observe and analyze significant differences in the behaviour of different pruning methods. The code is available at: https://github.com/IST-DASLab/sparse-imagenet-transfer.}, author = {Iofinova, Eugenia B and Peste, Elena-Alexandra and Kurtz, Mark and Alistarh, Dan-Adrian}, booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {New Orleans, LA, United States}, pages = {12256--12266}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{How well do sparse ImageNet models transfer?}}, doi = {10.1109/cvpr52688.2022.01195}, year = {2022}, } @inproceedings{14114, abstract = {Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer vision improve fairness by degrading the performance of classifiers across all groups (with increased degradation on the best performing groups). Extending the bias-variance decomposition for classification to fairness, we theoretically explain why the majority of fairness methods designed for low capacity models should not be used in settings involving high-capacity models, a scenario common to computer vision. We corroborate this analysis with extensive experimental support that shows that many of the fairness heuristics used in computer vision also degrade performance on the most disadvantaged groups. Building on these insights, we propose an adaptive augmentation strategy that, uniquely, of all methods tested, improves performance for the disadvantaged groups.}, author = {Zietlow, Dominik and Lohaus, Michael and Balakrishnan, Guha and Kleindessner, Matthaus and Locatello, Francesco and Scholkopf, Bernhard and Russell, Chris}, booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, isbn = {9781665469470}, issn = {2575-7075}, location = {New Orleans, LA, United States}, pages = {10400--10411}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers}}, doi = {10.1109/cvpr52688.2022.01016}, year = {2022}, } @inproceedings{18258, abstract = {Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.}, author = {Karlinsky, Leonid and Shtok, Joseph and Harary, Sivan and Schwartz, Eli and Aides, Amit and Feris, Rogerio and Giryes, Raja and Bronstein, Alexander}, booktitle = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, isbn = {9781728132945}, issn = {2575-7075}, location = {Long Beach, CA, United States}, publisher = {IEEE}, title = {{Repmet: Representative-based metric learning for classification and few-shot object detection}}, doi = {10.1109/cvpr.2019.00534}, year = {2020}, } @inproceedings{18259, abstract = {Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis approaches only address the scenario of a single category label per image. In this work, we propose a novel technique for synthesizing samples with multiple labels for the (yet unhandled) multi-label few-shot classification scenario. We propose to combine pairs of given examples in feature space, so that the resulting synthesized feature vectors will correspond to examples whose label sets are obtained through certain set operations on the label sets of the corresponding input pairs. Thus, our method is capable of producing a sample containing the intersection, union or set-difference of labels present in two input samples. As we show, these set operations generalize to labels unseen during training. This enables performing augmentation on examples of novel categories, thus, facilitating multi-label few-shot classifier learning. We conduct numerous experiments showing promising results for the label-set manipulation capabilities of the proposed approach, both directly (using the classification and retrieval metrics), and in the context of performing data augmentation for multi-label few-shot learning. We propose a benchmark for this new and challenging task and show that our method compares favorably to all the common baselines.}, author = {Alfassy, Amit and Karlinsky, Leonid and Aides, Amit and Shtok, Joseph and Harary, Sivan and Feris, Rogerio and Giryes, Raja and Bronstein, Alexander}, booktitle = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, isbn = {9781728132945}, issn = {2575-7075}, location = {Long Beach, CA, United States}, publisher = {IEEE}, title = {{Laso: Label-set operations networks for multi-label few-shot learning}}, doi = {10.1109/cvpr.2019.00671}, year = {2020}, } @inproceedings{18260, abstract = {We introduce the first completely unsupervised correspondence learning approach for deformable 3D shapes. Key to our model is the understanding that natural deformations (such as changes in pose) approximately preserve the metric structure of the surface, yielding a natural criterion to drive the learning process toward distortion-minimizing predictions. On this basis, we overcome the need for annotated data and replace it by a purely geometric criterion. The resulting learning model is class-agnostic, and is able to leverage any type of deformable geometric data for the training phase. In contrast to existing supervised approaches which specialize on the class seen at training time, we demonstrate stronger generalization as well as applicability to a variety of challenging settings. We showcase our method on a wide selection of correspondence benchmarks, where we outperform other methods in terms of accuracy, generalization, and efficiency.}, author = {Halimi, Oshri and Litany, Or and Rodola, Emanuele Rodola and Bronstein, Alexander and Kimmel, Ron}, booktitle = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, isbn = {9781728132945}, issn = {2575-7075}, location = {Long Beach, CA, United States}, publisher = {IEEE}, title = {{Unsupervised learning of dense shape correspondence}}, doi = {10.1109/cvpr.2019.00450}, year = {2020}, } @inproceedings{8186, abstract = {Numerous methods have been proposed for probabilistic generative modelling of 3D objects. However, none of these is able to produce textured objects, which renders them of limited use for practical tasks. In this work, we present the first generative model of textured 3D meshes. Training such a model would traditionally require a large dataset of textured meshes, but unfortunately, existing datasets of meshes lack detailed textures. We instead propose a new training methodology that allows learning from collections of 2D images without any 3D information. To do so, we train our model to explain a distribution of images by modelling each image as a 3D foreground object placed in front of a 2D background. Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set. A well-known problem when generating meshes with deep networks is the emergence of self-intersections, which are problematic for many use-cases. As a second contribution we therefore introduce a new generation process for 3D meshes that guarantees no self-intersections arise, based on the physical intuition that faces should push one another out of the way as they move. We conduct extensive experiments on our approach, reporting quantitative and qualitative results on both synthetic data and natural images. These show our method successfully learns to generate plausible and diverse textured 3D samples for five challenging object classes.}, author = {Henderson, Paul M and Tsiminaki, Vagia and Lampert, Christoph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, issn = {2575-7075}, location = {Virtual}, pages = {7498--7507}, publisher = {IEEE}, title = {{Leveraging 2D data to learn textured 3D mesh generation}}, doi = {10.1109/CVPR42600.2020.00752}, year = {2020}, } @inproceedings{10882, abstract = {We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider two actions: box verification [34], where the annotator verifies a box generated by an object detector, and manual box drawing. We explore two kinds of agents, one based on predicting the probability that a box will be positively verified, and the other based on reinforcement learning. We demonstrate that (1) our agents are able to learn efficient annotation strategies in several scenarios, automatically adapting to the image difficulty, the desired quality of the boxes, and the detector strength; (2) in all scenarios the resulting annotation dialogs speed up annotation compared to manual box drawing alone and box verification alone, while also outperforming any fixed combination of verification and drawing in most scenarios; (3) in a realistic scenario where the detector is iteratively re-trained, our agents evolve a series of strategies that reflect the shifting trade-off between verification and drawing as the detector grows stronger.}, author = {Uijlings, Jasper and Konyushkova, Ksenia and Lampert, Christoph and Ferrari, Vittorio}, booktitle = {2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, isbn = {9781538664209}, issn = {2575-7075}, location = {Salt Lake City, UT, United States}, pages = {9175--9184}, publisher = {IEEE}, title = {{Learning intelligent dialogs for bounding box annotation}}, doi = {10.1109/cvpr.2018.00956}, year = {2018}, } @inproceedings{18270, abstract = {The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly non-rigidly moving) 3D object from a single or multiple partial scans has received increasing attention in recent years. In this work, we propose a novel learning-based method for the completion of partial shapes. Unlike the majority of existing approaches, our method focuses on objects that can undergo non-rigid deformations. The core of our method is a variational autoencoder with graph convolutional operations that learns a latent space for complete realistic shapes. At inference, we optimize to find the representation in this latent space that best fits the generated shape to the known partial input. The completed shape exhibits a realistic appearance on the unknown part. We show promising results towards the completion of synthetic and real scans of human body and face meshes exhibiting different styles of articulation and partiality.}, author = {Litany, Or and Bronstein, Alexander and Bronstein, Michael and Makadia, Ameesh}, booktitle = {2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, isbn = {9781538664216}, issn = {2575-7075}, location = {Salt Lake City, UT, United States}, publisher = {IEEE}, title = {{Deformable shape completion with graph convolutional autoencoders}}, doi = {10.1109/cvpr.2018.00202}, year = {2018}, }