This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.
We study the problem of localizing audio-visual events that are both audible and visible in a video. Existing works focus on encoding and aligning audio and visual features at the segment level while neglecting informative correlation between segments of the two modalities and between multi-scale event proposals. We propose a novel MultiModulation Network (M2N) to learn the above correlation and leverage it as semantic guidance to modulate the related auditory, visual, and fused features. In particular, during feature encoding, we propose cross-modal normalization and intra-modal normalization. The former modulates the features of two modalities by establishing and exploiting the cross-modal relationship. The latter modulates the features of a single modality with the event-relevant semantic guidance of the same modality. In the fusion stage,we propose a multi-scale proposal modulating module and a multi-alignment segment modulating module to introduce multi-scale event proposals and enable dense matching between cross-modal segments. With the auditory, visual, and fused features modulated by the correlation information regarding audio-visual events, M2N performs accurate event localization. Extensive experiments conducted on the AVE dataset demonstrate that our proposed method outperforms the state of the art in both supervised event localization and cross-modality localization.
An important scenario for image quality assessment (IQA) is to evaluate image restoration (IR) algorithms. The state-of-the-art approaches adopt a full-reference paradigm that compares restored images with their corresponding pristine-quality images. However, pristine-quality images are usually unavailable in blind image restoration tasks and real-world scenarios. In this paper, we propose a practical solution named degraded-reference IQA (DR-IQA), which exploits the inputs of IR models, degraded images, as references. Specifically, we extract reference information from degraded images by distilling knowledge from pristine-quality images. The distillation is achieved through learning a reference space, where various degraded images are encouraged to share the same feature statistics with pristine-quality images. And the reference space is optimized to capture deep image priors that are useful for quality assessment. Note that pristine-quality images are only used during training. Our work provides a powerful and differentiable metric for blind IRs, especially for GAN-based methods. Extensive experiments show that our results can even be close to the performance of full-reference settings.
Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly and even mislead the decision process in real-life applications. We propose to remove the bias information misused by the target task with a cross-sample adversarial debiasing (CSAD) method. CSAD explicitly extracts target and bias features disentangled from the latent representation generated by a feature extractor and then learns to discover and remove the correlation between the target and bias features. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. Moreover, we propose joint content and local structural representation learning to boost mutual information estimation for better performance. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
Recent research has witnessed advances in facial image editing tasks including face swapping and face reenactment. However, these methods are confined to dealing with one specific task at a time. In addition, for video facial editing, previous methods either simply apply transformations frame by frame or utilize multiple frames in a concatenated or iterative fashion, which leads to noticeable visual flickers. In this paper, we propose a unified temporally consistent facial video editing framework termed UniFaceGAN. Based on a 3D reconstruction model and a simple yet efficient dynamic training sample selection mechanism, our framework is designed to handle face swapping and face reenactment simultaneously. To enforce the temporal consistency, a novel 3D temporal loss constraint is introduced based on the barycentric coordinate interpolation. Besides, we propose a region-aware conditional normalization layer to replace the traditional AdaIN or SPADE to synthesize more context-harmonious results. Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article. This task remains challenging as it is difficult to learn the association between named entities and visual cues due to the long-tail distribution of named entities. Furthermore, the complexity of the article brings difficulty in extracting fine-grained relationships between entities to generate informative event descriptions about the image. To tackle these challenges, we propose a novel approach that constructs a multi-modal knowledge graph to associate the visual objects with named entities and capture the relationship between entities simultaneously with the help of external knowledge collected from the web. Specifically, we build a text sub-graph by extracting named entities and their relationships from the article, and build an image sub-graph by detecting the objects in the image. To connect these two sub-graphs, we propose a cross-modal entity matching module trained using a knowledge base that contains Wikipedia entries and the corresponding images. Finally, the multi-modal knowledge graph is integrated into the captioning model via a graph attention mechanism. Extensive experiments on both GoodNews and NYTimes800k datasets demonstrate the effectiveness of our method.
How to model fine-grained spatial-temporal dynamics in videos has been a challenging problem for action recognition. It requires learning deep and rich features with superior distinctiveness for the subtle and abstract motions. Most existing methods generate features of a layer in a pure feedforward manner, where the information moves in one direction from inputs to outputs. And they rely on stacking more layers to obtain more powerful features, bringing extra non-negligible overheads. In this paper, we propose an Adaptive Recursive Circle (ARC) framework, a fine-grained decorator for pure feedforward layers. It inherits the operators and parameters of the original layer but is slightly different in the use of those operators and parameters. Specifically, the input of the layer is treated as an evolving state, and its update is alternated with the feature generation. At each recursive step, the input state is enriched by the previously generated features and the feature generation is made with the newly updated input state. We hope the ARC framework can facilitate fine-grained action recognition by introducing deeply refined features and multi-scale receptive fields at a low cost. Significant improvements over feedforward baselines are observed on several benchmarks. For example, an ARC-equipped TSM-ResNet18 outperforms TSM-ResNet50 with 48% fewer FLOPs and 52% model parameters on Something-Something V1 and Diving48.
Contrastive self-supervised learning (SSL) has achieved great success in unsupervised visual representation learning by maximizing the similarity between two augmented views of the same image (positive pairs) and simultaneously contrasting other different images (negative pairs). However, this type of methods, such as SimCLR and MoCo, relies heavily on a large number of negative pairs and thus requires either large batches or memory banks. In contrast, some recent non-contrastive SSL methods, such as BYOL and SimSiam, attempt to discard negative pairs by introducing asymmetry and show remarkable performance. Unfortunately, to avoid collapsed solutions caused by not using negative pairs, these methods require sophisticated asymmetry designs. In this paper, we argue that negative pairs are still necessary but one is sufficient, i.e., triplet is all you need. A simple triplet-based loss can achieve surprisingly good performance without requiring large batches or asymmetry. Moreover, we observe that unsupervised visual representation learning can gain significantly from randomness. Based on this observation, we propose a simple plug-in RandOm MApping (ROMA) strategy by randomly mapping samples into other spaces and enforcing these randomly projected samples to satisfy the same correlation requirement. The proposed ROMA strategy not only achieves the state-of-the-art performance in conjunction with the triplet-based loss, but also can further effectively boost other SSL methods.