Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image correspond to the
same object. Such a heavily curated constraint becomes immediately infeasible when pre-trained on more complex scene images with many objects. To overcome this limitation, we introduce Object-level Representation Learning (ORL), a new self-supervised learning framework towards scene images. Our key insight is to leverage image-level self-supervised pre-training as the prior to discover object-level semantic correspondence, thus realizing object-level representation learning from scene images. Extensive experiments on COCO show that ORL significantly improves the performance of self-supervised learning on scene images, even surpassing supervised ImageNet pre-training on several downstream tasks. Furthermore, ORL improves the downstream performance when more unlabeled scene images are available, demonstrating its great potential of harnessing unlabeled data in the wild. We hope our approach can motivate future research on more general-purpose unsupervised representation learning from scene data. Project page: https://www.mmlab-ntu.com/project/orl/.
Most existing research on domain generalization assumes source data gathered from multiple domains are fully annotated. However, in real-world applications, we might have only a few labels available from each source domain due to high annotation cost
, along with abundant unlabeled data that are much easier to obtain. In this work, we investigate semi-supervised domain generalization (SSDG), a more realistic and practical setting. Our proposed approach, StyleMatch, is inspired by FixMatch, a state-of-the-art semi-supervised learning method based on pseudo-labeling, with several new ingredients tailored to solve SSDG. Specifically, 1) to mitigate overfitting in the scarce labeled source data while improving robustness against noisy pseudo labels, we introduce stochastic modeling to the classifiers weights, seen as class prototypes, with Gaussian distributions. 2) To enhance generalization under domain shift, we upgrade FixMatchs two-view consistency learning paradigm based on weak and strong augmentations to a multi-view version with style augmentation as the third complementary view. To provide a comprehensive study and evaluation, we establish two SSDG benchmarks, which cover a wide range of strong baseline methods developed in relevant areas including domain generalization and semi-supervised learning. Extensive experiments demonstrate that StyleMatch achieves the best out-of-distribution generalization performance in the low-data regime. We hope our approach and benchmarks can pave the way for future research on data-efficient and generalizable learning systems.
Camera trapping is increasingly used to monitor wildlife, but this technology typically requires extensive data annotation. Recently, deep learning has significantly advanced automatic wildlife recognition. However, current methods are hampered by a
dependence on large static data sets when wildlife data is intrinsically dynamic and involves long-tailed distributions. These two drawbacks can be overcome through a hybrid combination of machine learning and humans in the loop. Our proposed iterative human and automated identification approach is capable of learning from wildlife imagery data with a long-tailed distribution. Additionally, it includes self-updating learning that facilitates capturing the community dynamics of rapidly changing natural systems. Extensive experiments show that our approach can achieve a ~90% accuracy employing only ~20% of the human annotations of existing approaches. Our synergistic collaboration of humans and machines transforms deep learning from a relatively inefficient post-annotation tool to a collaborative on-going annotation tool that vastly relieves the burden of human annotation and enables efficient and constant model updates.
Stereophonic audio, especially binaural audio, plays an essential role in immersive viewing environments. Recent research has explored generating visually guided stereophonic audios supervised by multi-channel audio collections. However, due to the r
equirement of professional recording devices, existing datasets are limited in scale and variety, which impedes the generalization of supervised methods in real-world scenarios. In this work, we propose PseudoBinaural, an effective pipeline that is free of binaural recordings. The key insight is to carefully build pseudo visual-stereo pairs with mono data for training. Specifically, we leverage spherical harmonic decomposition and head-related impulse response (HRIR) to identify the relationship between spatial locations and received binaural audios. Then in the visual modality, corresponding visual cues of the mono data are manually placed at sound source positions to form the pairs. Compared to fully-supervised paradigms, our binaural-recording-free pipeline shows great stability in cross-dataset evaluation and achieves comparable performance under subjective preference. Moreover, combined with binaural recordings, our method is able to further boost the performance of binaural audio generation under supervised settings.
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d.~assumption on source/target data, which is often violat
ed in practice due to domain shift. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Since first introduced in 2011, research in DG has made great progresses. In particular, intensive research in this topic has led to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, just to name a few; and has covered various vision applications such as object recognition, segmentation, action recognition, and person re-identification. In this paper, for the first time a comprehensive literature review is provided to summarize the developments in DG for computer vision over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other research fields like domain adaptation and transfer learning. Second, we conduct a thorough review into existing methods and present a categorization based on their methodologies and motivations. Finally, we conclude this survey with insights and discussions on future research directions.
Knowledge distillation, which involves extracting the dark knowledge from a teacher network to guide the learning of a student network, has emerged as an essential technique for model compression and transfer learning. Unlike previous works that focu
s on the accuracy of student network, here we study a little-explored but important question, i.e., knowledge distillation efficiency. Our goal is to achieve a performance comparable to conventional knowledge distillation with a lower computation cost during training. We show that the UNcertainty-aware mIXup (UNIX) can serve as a clean yet effective solution. The uncertainty sampling strategy is used to evaluate the informativeness of each training sample. Adaptive mixup is applied to uncertain samples to compact knowledge. We further show that the redundancy of conventional knowledge distillation lies in the excessive learning of easy samples. By combining uncertainty and mixup, our approach reduces the redundancy and makes better use of each query to the teacher network. We validate our approach on CIFAR100 and ImageNet. Notably, with only 79% computation cost, we outperform conventional knowledge distillation on CIFAR100 and achieve a comparable result on ImageNet.
Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies in this track mainly focus on intra-image invariance learning. The learning typically uses rich intra-image transformations to
construct positive pairs and then maximizes agreement using a contrastive loss. The merits of inter-image invariance, conversely, remain much less explored. One major obstacle to exploit inter-image invariance is that it is unclear how to reliably construct inter-image positive pairs, and further derive effective supervision from them since there are no pair annotations available. In this work, we present a rigorous and comprehensive study on inter-image invariance learning from three main constituting components: pseudo-label maintenance, sampling strategy, and decision boundary design. Through carefully-designed comparisons and analysis, we propose a unified and generic framework that supports the integration of unsupervised intra- and inter-image invariance learning. With all the obtained recipes, our final model, namely InterCLR, shows consistent improvements over state-of-the-art intra-image invariance learning methods on multiple standard benchmarks. Codes will be released at https://github.com/open-mmlab/OpenSelfSup.
Joint clustering and feature learning methods have shown remarkable performance in unsupervised representation learning. However, the training schedule alternating between feature clustering and network parameters update leads to unstable learning of
visual representations. To overcome this challenge, we propose Online Deep Clustering (ODC) that performs clustering and network update simultaneously rather than alternatingly. Our key insight is that the cluster centroids should evolve steadily in keeping the classifier stably updated. Specifically, we design and maintain two dynamic memory modules, i.e., samples memory to store samples labels and features, and centroids memory for centroids evolution. We break down the abrupt global clustering into steady memory update and batch-wise label re-assignment. The process is integrated into network update iterations. In this way, labels and the network evolve shoulder-to-shoulder rather than alternatingly. Extensive experiments demonstrate that ODC stabilizes the training process and boosts the performance effectively. Code: https://github.com/open-mmlab/OpenSelfSup.
Knowledge distillation, which involves extracting the dark knowledge from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning. Unlike previous works that expl
oit architecture-specific cues such as activation and attention for distillation, here we wish to explore a more general and model-agnostic approach for extracting richer dark knowledge from the pre-trained teacher model. We show that the seemingly different self-supervision task can serve as a simple yet powerful solution. For example, when performing contrastive learning between transformed entities, the noisy predictions of the teacher network reflect its intrinsic composition of semantic and pose information. By exploiting the similarity between those self-supervision signals as an auxiliary task, one can effectively transfer the hidden information from the teacher to the student. In this paper, we discuss practical ways to exploit those noisy self-supervision signals with selective transfer for distillation. We further show that self-supervision signals improve conventional distillation with substantial gains under few-shot and noisy-label scenarios. Given the richer knowledge mined from self-supervision, our knowledge distillation approach achieves state-of-the-art performance on standard benchmarks, i.e., CIFAR100 and ImageNet, under both similar-architecture and cross-architecture settings. The advantage is even more pronounced under the cross-architecture setting, where our method outperforms the state of the art CRD by an average of 2.3% in accuracy rate on CIFAR100 across six different teacher-student pairs.
Existing unconditional generative models mainly focus on modeling general objects, such as faces and indoor scenes. Fashion textures, another important type of visual elements around us, have not been extensively studied. In this work, we propose an
effective generative model for fashion textures and also comprehensively investigate the key components involved: internal representation, latent space sampling and the generator architecture. We use Gram matrix as a suitable internal representation for modeling realistic fashion textures, and further design two dedicated modules for modulating Gram matrix into a low-dimension vector. Since fashion textures are scale-dependent, we propose a recursive auto-encoder to capture the dependency between multiple granularity levels of texture feature. Another important observation is that fashion textures are multi-modal. We fit and sample from a Gaussian mixture model in the latent space to improve the diversity of the generated textures. Extensive experiments demonstrate that our approach is capable of synthesizing more realistic and diverse fashion textures over other state-of-the-art methods.
