Papers

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged in to the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.

poster session 3 @ red 3, poster session 7 @ red 3, oral session 7 @ red 3, poster session 3, poster session 7, oral session 7

Model generalization to the unseen scenes is crucial to real-world applications, such as autonomous driving, which requires robust vision systems. To enhance the model generalization, domain generalization through learning the domain-invariant representation has been widely studied. However, most existing works learn the shared feature space within multi-source domains but ignore the characteristic of the feature itself (e.g., the feature sensitivity to the domain-specific style). Therefore, we propose the Domain-invariant Representation Learning (DIRL) for domain generalization which utilizes the feature sensitivity as the feature prior to guide the enhancement of the model generalization capability. The guidance reflects in two folds: 1) Feature re-calibration that introduces the Prior Guided Attention Module (PGAM) to emphasize the insensitive features and suppress the sensitive features. 2): Feature whiting that proposes the Guided Feature Whiting (GFW) to remove the feature correlations which are sensitive to the domain-specific style. We construct the domain-invariant representation which suppresses the effect of the domain-specific style on the quality and correlation of the features. As a result, our method is simple yet effective, and can enhance the robustness of various backbone networks with little computational cost. Extensive experiments over multiple domains generalizable segmentation tasks show the superiority of our approach to other methods.

poster session 3 @ red 3, poster session 7 @ red 3, oral session 7 @ red 3, poster session 3, poster session 7, oral session 7

In this paper, we propose a framework centering around a novel architecture called the Event Decomposition Recom-position Network (EDRNet) to tackle the Audio-Visual Event(AVE) localization problem in the supervised and weakly supervised settings. AVEs in the real world exhibit common unraveling patterns (termed asEvent Progress Checkpoints(EPC)), which humans can perceive through the cooperation of their auditory and visual senses. Unlike earlier methods which attempt to recognize entire event sequences, the EDR-Net models EPCs and inter-EPC relationships using stacked temporal convolutions. Based on the postulation that EPCrepresentations are theoretically consistent for an event category, we introduce the State Machine Based Video Fusion, a novel augmentation technique that blends source videos using different EPC template sequences. Additionally, we design a new loss function called the Land-Shore-Sea loss to compactify continuous foreground and background representations. Lastly, to alleviate the issue of confusing events during weak supervision, we propose a prediction stabilizationmethod called Bag to Instance Label Correction. Experimentson the AVE dataset show that our collective framework out-performs the state-of-the-art by a sizable margin.

poster session 3 @ red 3, poster session 7 @ red 3, oral session 7 @ red 3, poster session 3, poster session 7, oral session 7