REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints

Deep models deployed on edge devices frequently encounter resource variability, which arises from fluctuating energy levels, timing constraints, or prioritization of other critical tasks within the system. State-of-the-art machine learning pipelines generate resource-agnostic models, not capable to adapt at runtime. In this work we introduce Resource-Efficient Deep Subnetworks (REDS) to tackle model adaptation to variable resources. In contrast to the state-of-the-art, REDS use structured sparsity constructively by exploiting permutation invariance of neurons, which allows for hardware-specific optimizations. Specifically, REDS achieve computational efficiency by (1) skipping sequential computational blocks identified by a novel iterative knapsack optimizer, and (2) leveraging simple math to re-arrange the order of operations in REDS computational graph to take advantage of the data cache. REDS support conventional deep networks frequently deployed on the edge and provide computational benefits even for small and simple networks. We evaluate REDS on six benchmark architectures trained on the Google Speech Commands, FMNIST and CIFAR10 datasets, and test on four off-the-shelf mobile and embedded hardware platforms. We provide a theoretical result and empirical evidence for REDS outstanding performance in terms of submodels' test set accuracy, and demonstrate an adaptation time in response to dynamic resource constraints of under 40$\mu$s, utilizing a 2-layer fully-connected network on Arduino Nano 33 BLE Sense.

Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images

Distribution shifts are characterized by differences between the training and test data distributions. They can significantly reduce the accuracy of machine learning models deployed in real-world scenarios. This paper explores the distribution shift problem when classifying pollen grains from microscopic images collected in the wild with a low-cost camera sensor. We leverage the domain knowledge that geometric features are highly important for accurate pollen identification and introduce two novel geometric image augmentation techniques to significantly narrow the accuracy gap between the model performance on the train and test datasets. In particular, we show that Tenengrad and ImageToSketch filters are highly effective to balance the shape and texture information while leaving out unimportant details that may confuse the model. Extensive evaluations on various model architectures demonstrate a consistent improvement of the model generalization to field data of up to 14% achieved by the geometric augmentation techniques when compared to a wide range of standard image augmentations. The approach is validated through an ablation study using pollen hydration tests to recover the shape of dry pollen grains. The proposed geometric augmentations also receive the highest scores according to the affinity and diversity measures from the literature.

Representing Input Transformations by Low-Dimensional Parameter Subspaces

Deep models lack robustness to simple input transformations such as rotation, scaling, and translation, unless they feature a particular invariant architecture or undergo specific training, e.g., learning the desired robustness from data augmentations. Alternatively, input transformations can be treated as a domain shift problem, and solved by post-deployment model adaptation. Although a large number of methods deal with transformed inputs, the fundamental relation between input transformations and optimal model weights is unknown. In this paper, we put forward the configuration subspace hypothesis that model weights optimal for parameterized continuous transformations can reside in low-dimensional linear subspaces. We introduce subspace-configurable networks to learn these subspaces and observe their structure and surprisingly low dimensionality on all tested transformations, datasets and architectures from computer vision and audio signal processing domains. Our findings enable efficient model reconfiguration, especially when limited storage and computing resources are at stake.

DataComp: In search of the next generation of multimodal datasets

Large multimodal datasets have been instrumental in recent breakthroughs such as CLIP, Stable Diffusion, and GPT-4. At the same time, datasets rarely receive the same research attention as model architectures or training algorithms. To address this shortcoming in the machine learning ecosystem, we introduce DataComp, a benchmark where the training code is fixed and researchers innovate by proposing new training sets. We provide a testbed for dataset experiments centered around a new candidate pool of 12.8B image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing on 38 downstream test sets. Our benchmark consists of multiple scales, with four candidate pool sizes and associated compute budgets ranging from 12.8M to 12.8B samples seen during training. This multi-scale design facilitates the study of scaling trends and makes the benchmark accessible to researchers with varying resources. Our baseline experiments show that the DataComp workflow is a promising way of improving multimodal datasets. We introduce DataComp-1B, a dataset created by applying a simple filtering algorithm to the 12.8B candidate pool. The resulting 1.4B subset enables training a CLIP ViT-L/14 from scratch to 79.2% zero-shot accuracy on ImageNet. Our new ViT-L/14 model outperforms a larger ViT-g/14 trained on LAION-2B by 0.7 percentage points while requiring 9x less training compute. We also outperform OpenAI's CLIP ViT-L/14 by 3.7 percentage points, which is trained with the same compute budget as our model. These gains highlight the potential for improving model performance by carefully curating training sets. We view DataComp-1B as only the first step and hope that DataComp paves the way toward the next generation of multimodal datasets.

The Role of Pre-training Data in Transfer Learning

The transfer learning paradigm of model pre-training and subsequent fine-tuning produces high-accuracy models. While most studies recommend scaling the pre-training size to benefit most from transfer learning, a question remains: what data and method should be used for pre-training? We investigate the impact of pre-training data distribution on the few-shot and full fine-tuning performance using 3 pre-training methods (supervised, contrastive language-image and image-image), 7 pre-training datasets, and 9 downstream datasets. Through extensive controlled experiments, we find that the choice of the pre-training data source is essential for the few-shot transfer, but its role decreases as more data is made available for fine-tuning. Additionally, we explore the role of data curation and examine the trade-offs between label noise and the size of the pre-training dataset. We find that using 2000X more pre-training data from LAION can match the performance of supervised ImageNet pre-training. Furthermore, we investigate the effect of pre-training methods, comparing language-image contrastive vs. image-image contrastive, and find that the latter leads to better downstream accuracy

REPAIR: REnormalizing Permuted Activations for Interpolation Repair

In this paper we look into the conjecture of Entezari et al.(2021) which states that if the permutation invariance of neural networks is taken into account, then there is likely no loss barrier to the linear interpolation between SGD solutions. First, we observe that neuron alignment methods alone are insufficient to establish low-barrier linear connectivity between SGD solutions due to a phenomenon we call variance collapse: interpolated deep networks suffer a collapse in the variance of their activations, causing poor performance. Next, we propose REPAIR (REnormalizing Permuted Activations for Interpolation Repair) which mitigates variance collapse by rescaling the preactivations of such interpolated networks. We explore the interaction between our method and the choice of normalization layer, network width, and depth, and demonstrate that using REPAIR on top of neuron alignment methods leads to 60%-100% relative barrier reduction across a wide variety of architecture families and tasks. In particular, we report a 74% barrier reduction for ResNet50 on ImageNet and 90% barrier reduction for ResNet18 on CIFAR10.

Studying the impact of magnitude pruning on contrastive learning methods

We study the impact of different pruning techniques on the representation learned by deep neural networks trained with contrastive loss functions. Our work finds that at high sparsity levels, contrastive learning results in a higher number of misclassified examples relative to models trained with traditional cross-entropy loss. To understand this pronounced difference, we use metrics such as the number of PIEs (Hooker et al., 2019), Q-Score (Kalibhat et al., 2022), and PD-Score (Baldock et al., 2021) to measure the impact of pruning on the learned representation quality. Our analysis suggests the schedule of the pruning method implementation matters. We find that the negative impact of sparsity on the quality of the learned representation is the highest when pruning is introduced early on in the training phase.

Understanding the effect of sparsity on neural networks robustness

This paper examines the impact of static sparsity on the robustness of a trained network to weight perturbations, data corruption, and adversarial examples. We show that, up to a certain sparsity achieved by increasing network width and depth while keeping the network capacity fixed, sparsified networks consistently match and often outperform their initially dense versions. Robustness and accuracy decline simultaneously for very high sparsity due to loose connectivity between network layers. Our findings show that a rapid robustness drop caused by network compression observed in the literature is due to a reduced network capacity rather than sparsity.

Deep Neural Network Pruning for Nuclei Instance Segmentation in Hematoxylin & Eosin-Stained Histological Images

Recently, pruning deep neural networks (DNNs) has received a lot of attention for improving accuracy and generalization power, reducing network size, and increasing inference speed on specialized hardwares. Although pruning was mainly tested on computer vision tasks, its application in the context of medical image analysis has hardly been explored. This work investigates the impact of well-known pruning techniques, namely layer-wise and network-wide magnitude pruning, on the nuclei instance segmentation performance in histological images. Our utilized instance segmentation model consists of two main branches: (1) a semantic segmentation branch, and (2) a deep regression branch. We investigate the impact of weight pruning on the performance of both branches separately and on the final nuclei instance segmentation result. Evaluated on two publicly available datasets, our results show that layer-wise pruning delivers slightly better performance than networkwide pruning for small compression ratios (CRs) while for large CRs, network-wide pruning yields superior performance. For semantic segmentation, deep regression and final instance segmentation, 93.75 %, 95 %, and 80 % of the model weights can be pruned by layer-wise pruning with less than 2 % reduction in the performance of respective models.