Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD) generalization. Although many debiasing approaches have been proposed to ensure correct predictions from biased datasets, few studies have considered learning latent embedding consisting of intrinsic and biased attributes that contribute to improved performance and explain how the model pays attention to attributes. In this paper, we propose a novel debiasing framework, Debiasing Global Workspace, introducing attention-based information bottlenecks for learning compositional representations of attributes without defining specific bias types. Based on our observation that learning shape-centric representation helps robust performance on OOD datasets, we adopt those abilities to learn robust and generalizable representations of decomposable latent embeddings corresponding to intrinsic and biasing attributes. We conduct comprehensive evaluations on biased datasets, along with both quantitative and qualitative analyses, to showcase our approach's efficacy in attribute-centric representation learning and its ability to differentiate between intrinsic and bias-related features.
In this paper, we address the problem of adapting models from a source domain to a target domain, a task that has become increasingly important due to the brittle generalization of deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic toolbox data augmentations in cases of limited target data availability. We consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA, which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments on a variety of benchmarks, distribution shifts and image corruptions, we find that SiSTA produces significantly improved generalization over existing baselines in face attribute detection and multi-class object recognition. Furthermore, SiSTA performs competitively to models obtained by training on larger target datasets. Our codes can be accessed at https://github.com/Rakshith-2905/SiSTA.
This paper investigates the challenge of learning image manifolds, specifically pose manifolds, of 3D objects using limited training data. It proposes a DNN approach to manifold learning and for predicting images of objects for novel, continuous 3D rotations. The approach uses two distinct concepts: (1) Geometric Style-GAN (Geom-SGAN), which maps images to low-dimensional latent representations and maintains the (first-order) manifold geometry. That is, it seeks to preserve the pairwise distances between base points and their tangent spaces, and (2) uses Euler's elastica to smoothly interpolate between directed points (points + tangent directions) in the low-dimensional latent space. When mapped back to the larger image space, the resulting interpolations resemble videos of rotating objects. Extensive experiments establish the superiority of this framework in learning paths on rotation manifolds, both visually and quantitatively, relative to state-of-the-art GANs and VAEs.
Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. However, the finite encoding size restricts the model's representational power. Higher representational power is needed to go from representing a single given image to representing large and diverse datasets. Our approach addresses this gap by representing an image with a polynomial function and eliminates the need for positional encodings. Therefore, to achieve a progressively higher degree of polynomial representation, we use element-wise multiplications between features and affine-transformed coordinate locations after every ReLU layer. The proposed method is evaluated qualitatively and quantitatively on large datasets like ImageNet. The proposed Poly-INR model performs comparably to state-of-the-art generative models without any convolution, normalization, or self-attention layers, and with far fewer trainable parameters. With much fewer training parameters and higher representative power, our approach paves the way for broader adoption of INR models for generative modeling tasks in complex domains. The code is available at \url{https://github.com/Rajhans0/Poly_INR}
Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network). Recently, additional variations for knowledge distillation, utilizing activation maps of intermediate layers as the source of knowledge, have been studied. Generally, in computer vision applications, it is seen that the feature activation learned by a higher capacity model contains richer knowledge, highlighting complete objects while focusing less on the background. Based on this observation, we leverage the dual ability of the teacher to accurately distinguish between positive (relevant to the target object) and negative (irrelevant) areas. We propose a new loss function for distillation, called angular margin-based distillation (AMD) loss. AMD loss uses the angular distance between positive and negative features by projecting them onto a hypersphere, motivated by the near angular distributions seen in many feature extractors. Then, we create a more attentive feature that is angularly distributed on the hypersphere by introducing an angular margin to the positive feature. Transferring such knowledge from the teacher network enables the student model to harness the higher discrimination of positive and negative features for the teacher, thus distilling superior student models. The proposed method is evaluated for various student-teacher network pairs on four public datasets. Furthermore, we show that the proposed method has advantages in compatibility with other learning techniques, such as using fine-grained features, augmentation, and other distillation methods.
Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model. Knowledge distillation (KD), on the other hand, is widely used for model compression and transfer learning, which involves using a larger network's implicit knowledge to guide the learning of a smaller network. At first glance, these two techniques seem very different, however, we found that "smoothness" is the connecting link between the two and is also a crucial attribute in understanding KD's interplay with mixup. Although many mixup variants and distillation methods have been proposed, much remains to be understood regarding the role of a mixup in knowledge distillation. In this paper, we present a detailed empirical study on various important dimensions of compatibility between mixup and knowledge distillation. We also scrutinize the behavior of the networks trained with a mixup in the light of knowledge distillation through extensive analysis, visualizations, and comprehensive experiments on image classification. Finally, based on our findings, we suggest improved strategies to guide the student network to enhance its effectiveness. Additionally, the findings of this study provide insightful suggestions to researchers and practitioners that commonly use techniques from KD. Our code is available at https://github.com/hchoi71/MIX-KD.
The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic data augmentations in cases of limited target data availability. In this paper, we consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA (Single-Shot Target Augmentations), which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments with a state-of-the-art domain adaptation method, we find that SiSTA produces improvements as high as 20\% over existing baselines under challenging shifts in face attribute detection, and that it performs competitively to oracle models obtained by training on a larger target dataset.
A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled data. In this paper, we focus on a challenging variant of this problem, where access to the original source data is restricted. While fully test-time adaptation (FTTA) and unsupervised domain adaptation (UDA) are closely related, the advances in UDA are not readily applicable to TTA, since most UDA methods require access to the source data. Hence, we propose a new approach, CATTAn, that bridges UDA and FTTA, by relaxing the need to access entire source data, through a novel deep subspace alignment strategy. With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation. Through extensive experimental evaluation on multiple 2D and 3D vision benchmarks (ImageNet-C, Office-31, OfficeHome, DomainNet, PointDA-10) and model architectures, we demonstrate significant gains in FTTA performance. Furthermore, we make a number of crucial findings on the utility of the alignment objective even with inherently robust models, pre-trained ViT representations and under low sample availability in the target domain.
Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant, yet in a task-specific manner. The proposed model improves the final feature's interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance as compared to the baseline and standard ResNet models while substantially improving interpretability.
Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge devices such as smartphones and wearable devices. To address this problem, knowledge distillation (KD) has been widely employed, that uses a pre-trained high capacity network to train a much smaller network, suitable for edge devices. In this paper, for the first time, we study the applicability and challenges of using KD for time-series data for wearable devices. Successful application of KD requires specific choices of data augmentation methods during training. However, it is not yet known if there exists a coherent strategy for choosing an augmentation approach during KD. In this paper, we report the results of a detailed study that compares and contrasts various common choices and some hybrid data augmentation strategies in KD based human activity analysis. Research in this area is often limited as there are not many comprehensive databases available in the public domain from wearable devices. Our study considers databases from small scale publicly available to one derived from a large scale interventional study into human activity and sedentary behavior. We find that the choice of data augmentation techniques during KD have a variable level of impact on end performance, and find that the optimal network choice as well as data augmentation strategies are specific to a dataset at hand. However, we also conclude with a general set of recommendations that can provide a strong baseline performance across databases.